diff --git a/i18n/locale/es_ES.json b/i18n/locale/es_ES.json index b0ecbc7..875e82a 100644 --- a/i18n/locale/es_ES.json +++ b/i18n/locale/es_ES.json @@ -1,9 +1,9 @@ { - "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", + "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Comparación de modelos\n> Obtén el ID del modelo (largo) en la sección de `Ver información del modelo` a continuación\n\nSe puede utilizar para comparar la similitud de la inferencia de dos modelos.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Extracción de modelo\n> Ingrese la ruta de un archivo de modelo grande en la carpeta 'logs'.\n\nAplicable cuando desea extraer un archivo de modelo pequeño después de entrenar a mitad de camino y no se guardó automáticamente, o cuando desea probar un modelo intermedio.", - "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", + "### Model fusion\nCan be used to test timbre fusion.": "### Fusión de modelos\nSe puede utilizar para fusionar diferentes voces.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Modificar la información del modelo\n> Solo admite archivos de modelos pequeños extraídos en la carpeta 'weights'.", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Paso 1. Complete la configuración del experimento.\nLos datos del experimento se almacenan en el directorio 'logs', con cada experimento en una carpeta separada. La ruta del nombre del experimento debe ingresarse manualmente y debe contener la configuración del experimento, los registros y los archivos del modelo entrenado.", "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Paso dos: Procesamiento de audio\n#### 1. Segmentación de audio\nRecorre automáticamente todos los archivos que se pueden decodificar en audio en la carpeta de entrenamiento y realiza la segmentación y normalización, generando 2 carpetas wav en el directorio del experimento; por ahora solo se admite el entrenamiento individual.", "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Paso tres: Comienza el entrenamiento\nCompleta la configuración de entrenamiento, comienza a entrenar el modelo y el índice.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Ver información del modelo\n> Solo aplicable a archivos de modelos pequeños extraídos de la carpeta 'weights'.", @@ -50,7 +50,7 @@ "Hidden": "Oculto", "ID of model A (long)": "ID del modelo A (largo)", "ID of model B (long)": "ID del modelo B (largo)", - "ID(long)": "ID(long)", + "ID(long)": "ID (largo)", "ID(short)": "ID (corto)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": "Si es >=3, entonces use el resultado del reconocimiento de tono de 'harvest' con filtro de mediana, el valor es el radio del filtro, su uso puede debilitar el sonido sordo", "Inference time (ms)": "Inferir tiempo (ms)", diff --git a/i18n/locale/fr_FR.json b/i18n/locale/fr_FR.json index cb222d9..da373ef 100644 --- a/i18n/locale/fr_FR.json +++ b/i18n/locale/fr_FR.json @@ -1,9 +1,9 @@ { - "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", + "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Comparaison des modèles\n> Pour obtenir l'ID du modèle (long), veuillez consulter la section `Voir les informations du modèle` ci-dessous.\n\nPeut être utilisé pour comparer la similarité des inférences entre deux modèles.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Extraction du modèle\n> Saisissez le chemin d'accès au modèle du grand fichier dans le dossier \"logs\".\n\nCette fonction est utile si vous souhaitez arrêter l'entrainement à mi-chemin et extraire et enregistrer manuellement un petit fichier de modèle, ou si vous souhaitez tester un modèle intermédiaire.", "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Modifier les informations du modèle\n> Uniquement pris en charge pour les petits fichiers de modèle extraits du dossier 'weights'.", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Étape 1. Remplissez la configuration expérimentale.\nLes données expérimentales sont stockées dans le dossier 'logs', avec chaque expérience ayant un dossier distinct. Entrez manuellement le chemin du nom de l'expérience, qui contient la configuration expérimentale, les journaux et les fichiers de modèle entraînés.", "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Deuxième étape : Traitement audio\n#### 1. Découpage de l'audio\nParcourez automatiquement tous les fichiers qui peuvent être décodés en audio dans le dossier d'entraînement et effectuez le découpage et la normalisation. Deux dossiers wav sont générés dans le répertoire de l'expérience. Pour le moment, seul l'entraînement individuel est pris en charge.", "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Troisième étape : Commencer l'entraînement\nRemplissez les paramètres d'entraînement, commencez à entraîner le modèle et l'index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Afficher les informations sur le modèle\n> Uniquement pour les petits fichiers de modèle extraits du dossier 'weights'.", @@ -50,7 +50,7 @@ "Hidden": "Caché", "ID of model A (long)": "ID du modèle A (long)", "ID of model B (long)": "ID du modèle B (long)", - "ID(long)": "ID(long)", + "ID(long)": "ID (long)", "ID(short)": "ID (court)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": "Si >=3 : appliquer un filtrage médian aux résultats de la reconnaissance de la hauteur de récolte. La valeur représente le rayon du filtre et peut réduire la respiration.", "Inference time (ms)": "Temps d'inférence (ms)", diff --git a/i18n/locale/it_IT.json b/i18n/locale/it_IT.json index 6e859ba..462f643 100644 --- a/i18n/locale/it_IT.json +++ b/i18n/locale/it_IT.json @@ -1,37 +1,37 @@ { "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Estrazione del modello\n> Inserire il percorso del modello di file di grandi dimensioni nella cartella \"logs\".", - "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", + "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nPuò essere utilizzato per testare la fusione timbrica.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Modifica le informazioni sul modello\n> Supportato solo per i file di modello di piccole dimensioni estratti dalla cartella 'weights'.", "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", - "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", - "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", + "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.", + "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Step 3. Start training.\nFill in the training settings and start training the model and index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Visualizza le informazioni sul modello\n> Supportato solo per file di modello piccoli estratti dalla cartella 'weights'.", - "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", - "Actually calculated": "实际计算", + "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).", + "Actually calculated": "Actually calculated", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "Regola il ridimensionamento dell'inviluppo del volume. ", - "Algorithmic delays (ms)": "算法延迟(ms)", + "Algorithmic delays (ms)": "Algorithmic delays (ms)", "All processes have been completed!": "Tutti i processi sono stati completati!", "Audio device": "Dispositivo audio", "Auto-detect index path and select from the dropdown": "Rileva automaticamente il percorso dell'indice e seleziona dal menu a tendina:", "Batch conversion. Enter the folder containing the audio files to be converted or upload multiple audio files. The converted audio will be output in the specified folder (default: 'opt').": "Conversione massiva. Inserisci il percorso della cartella che contiene i file da convertire o carica più file audio. I file convertiti finiranno nella cartella specificata. (default: opt) ", - "Batch inference": "批量推理", + "Batch inference": "Batch inference", "Batch processing for vocal accompaniment separation using the UVR5 model.
Example of a valid folder path format: D:\\path\\to\\input\\folder (copy it from the file manager address bar).
The model is divided into three categories:
1. Preserve vocals: Choose this option for audio without harmonies. It preserves vocals better than HP5. It includes two built-in models: HP2 and HP3. HP3 may slightly leak accompaniment but preserves vocals slightly better than HP2.
2. Preserve main vocals only: Choose this option for audio with harmonies. It may weaken the main vocals. It includes one built-in model: HP5.
3. De-reverb and de-delay models (by FoxJoy):
  (1) MDX-Net: The best choice for stereo reverb removal but cannot remove mono reverb;
 (234) DeEcho: Removes delay effects. Aggressive mode removes more thoroughly than Normal mode. DeReverb additionally removes reverb and can remove mono reverb, but not very effectively for heavily reverberated high-frequency content.
De-reverb/de-delay notes:
1. The processing time for the DeEcho-DeReverb model is approximately twice as long as the other two DeEcho models.
2. The MDX-Net-Dereverb model is quite slow.
3. The recommended cleanest configuration is to apply MDX-Net first and then DeEcho-Aggressive.": "Elaborazione batch per la separazione dell'accompagnamento vocale utilizzando il modello UVR5.
Esempio di un formato di percorso di cartella valido: D:\\path\\to\\input\\folder (copialo dalla barra degli indirizzi del file manager).
Il modello è suddiviso in tre categorie:
1. Conserva la voce: scegli questa opzione per l'audio senza armonie.
2. Mantieni solo la voce principale: scegli questa opzione per l'audio con armonie.
3. Modelli di de-riverbero e de-delay (di FoxJoy):
  (1) MDX-Net: la scelta migliore per la rimozione del riverbero stereo ma non può rimuovere il riverbero mono;

Note di de-riverbero/de-delay:
1. Il tempo di elaborazione per il modello DeEcho-DeReverb è circa il doppio rispetto agli altri due modelli DeEcho.
2. Il modello MDX-Net-Dereverb è piuttosto lento.
3. La configurazione più pulita consigliata consiste nell'applicare prima MDX-Net e poi DeEcho-Aggressive.", "Batch size per GPU": "Dimensione batch per GPU:", "Cache all training sets to GPU memory. Caching small datasets (less than 10 minutes) can speed up training, but caching large datasets will consume a lot of GPU memory and may not provide much speed improvement": "Memorizza nella cache tutti i set di addestramento nella memoria della GPU. ", - "Calculate": "计算", - "Choose sample rate of the device": "使用设备采样率", - "Choose sample rate of the model": "使用模型采样率", + "Calculate": "Calculate", + "Choose sample rate of the device": "Choose sample rate of the device", + "Choose sample rate of the model": "Choose sample rate of the model", "Convert": "Convertire", - "Device type": "设备类型", - "Enable phase vocoder": "启用相位声码器", - "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程", + "Device type": "Device type", + "Enable phase vocoder": "Enable phase vocoder", + "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1", "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2": "Inserisci gli indici GPU separati da '-', ad esempio 0-1-2 per utilizzare GPU 0, 1 e 2:", "Enter the experiment name": "Inserisci il nome dell'esperimento:", "Enter the path of the audio folder to be processed": "Immettere il percorso della cartella audio da elaborare:", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "Immettere il percorso della cartella audio da elaborare (copiarlo dalla barra degli indirizzi del file manager):", "Enter the path of the training folder": "Inserisci il percorso della cartella di addestramento:", - "Exist": "有", + "Exist": "Exist", "Export Onnx": "Esporta Onnx", "Export Onnx Model": "Esporta modello Onnx", "Export audio (click on the three dots in the lower right corner to download)": "Esporta audio (clicca sui tre puntini in basso a destra per scaricarlo)", @@ -43,46 +43,46 @@ "Fade length": "Lunghezza dissolvenza", "Fail": "失败", "Feature extraction": "Estrazione delle caratteristiche", - "Formant offset": "共振偏移", + "Formant offset": "Formant offset", "Fusion": "Fusione", "GPU Information": "Informazioni GPU", "General settings": "Impostazioni generali", - "Hidden": "不显示", - "ID of model A (long)": "A模型ID(长)", - "ID of model B (long)": "B模型ID(长)", - "ID(long)": "ID(long)", - "ID(short)": "ID(短)", + "Hidden": "Hidden", + "ID of model A (long)": "ID of model A (long)", + "ID of model B (long)": "ID of model B (long)", + "ID(long)": "ID (long)", + "ID(short)": "ID (short)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": "Se >=3: applica il filtro mediano ai risultati del pitch raccolto. ", "Inference time (ms)": "Tempo di inferenza (ms)", "Inferencing voice": "Voce di inferenza:", - "Information": "信息", + "Information": "Information", "Input device": "Dispositivo di input", "Input noise reduction": "Riduzione del rumore in ingresso", - "Input voice monitor": "输入监听", - "Link index to outside folder": "链接索引到外部", + "Input voice monitor": "Input voice monitor", + "Link index to outside folder": "Link index to outside folder", "Load model": "Carica modello", "Load pre-trained base model D path": "Carica il percorso D del modello base pre-addestrato:", "Load pre-trained base model G path": "Carica il percorso G del modello base pre-addestrato:", "Loudness factor": "fattore di sonorità", "Model": "Modello", - "Model Author": "模型作者", - "Model Author (Nullable)": "模型作者(可空)", + "Model Author": "Model Author", + "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "Inferenza del modello", "Model architecture version": "Versione dell'architettura del modello:", - "Model info": "模型信息", + "Model info": "Model info", "Model information to be modified": "Informazioni sul modello da modificare:", "Model information to be placed": "Informazioni sul modello da posizionare:", - "Model name": "模型名", + "Model name": "Model name", "Modify": "Modificare", - "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "也可批量输入音频文件, 二选一, 优先读文件夹", + "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "Multiple audio files can also be imported. If a folder path exists, this input is ignored.", "No": "NO", "None": "None", - "Not exist": "无", - "Number of CPU processes used for harvest pitch algorithm": "harvest进程数", + "Not exist": "Not exist", + "Number of CPU processes used for harvest pitch algorithm": "Number of CPU processes used for harvest pitch algorithm", "Number of CPU processes used for pitch extraction and data processing": "Numero di processi CPU utilizzati per l'estrazione del tono e l'elaborazione dei dati:", "One-click training": "Addestramento con un clic", "Onnx Export Path": "Percorso di esportazione Onnx:", - "Output converted voice": "输出变声", + "Output converted voice": "Output converted voice", "Output device": "Dispositivo di uscita", "Output information": "Informazioni sull'uscita", "Output noise reduction": "Riduzione del rumore in uscita", @@ -91,22 +91,22 @@ "Path to Model B": "Percorso per il modello B:", "Path to the feature index file. Leave blank to use the selected result from the dropdown": "Percorso del file di indice delle caratteristiche. ", "Performance settings": "Impostazioni delle prestazioni", - "Pitch detection algorithm": "音高算法", - "Pitch guidance (f0)": "音高引导(f0)", + "Pitch detection algorithm": "Pitch detection algorithm", + "Pitch guidance (f0)": "Pitch guidance (f0)", "Pitch settings": "Impostazioni del tono", - "Please choose the .index file": "请选择index文件", - "Please choose the .pth file": "请选择pth 文件", + "Please choose the .index file": "Please choose the .index file", + "Please choose the .pth file": "Please choose the .pth file", "Please specify the speaker/singer ID": "Si prega di specificare l'ID del locutore/cantante:", "Process data": "Processa dati", "Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy": "Proteggi le consonanti senza voce e i suoni del respiro per evitare artefatti come il tearing nella musica elettronica. ", "RVC Model Path": "Percorso modello RVC:", - "Read from model": "从模型中读取", + "Read from model": "Read from model", "Refresh voice list and index path": "Aggiorna l'elenco delle voci e il percorso dell'indice", "Reload device list": "Ricaricare l'elenco dei dispositivi", "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "Ricampiona l'audio di output in post-elaborazione alla frequenza di campionamento finale. ", "Response threshold": "Soglia di risposta", "Sample length": "Lunghezza del campione", - "Sampling rate": "采样率", + "Sampling rate": "Sampling rate", "Save a small final model to the 'weights' folder at each save point": "Salva un piccolo modello finale nella cartella \"weights\" in ogni punto di salvataggio:", "Save file name (default: same as the source file)": "Salva il nome del file (predefinito: uguale al file di origine):", "Save frequency (save_every_epoch)": "Frequenza di salvataggio (save_every_epoch):", @@ -119,10 +119,10 @@ "Select the .index file": "Seleziona il file .index", "Select the .pth file": "Seleziona il file .pth", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "Seleziona l'algoritmo di estrazione del tono (\"pm\": estrazione più veloce ma risultato di qualità inferiore; \"harvest\": bassi migliori ma estremamente lenti; \"crepe\": qualità migliore ma utilizzo intensivo della GPU):", - "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU", - "Similarity": "相似度", - "Similarity (from 0 to 1)": "相似度(0到1)", - "Single inference": "单次推理", + "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU", + "Similarity": "Similarity", + "Similarity (from 0 to 1)": "Similarity (from 0 to 1)", + "Single inference": "Single inference", "Specify output folder": "Specifica la cartella di output:", "Specify the output folder for accompaniment": "Specificare la cartella di output per l'accompagnamento:", "Specify the output folder for vocals": "Specifica la cartella di output per le voci:", @@ -130,10 +130,10 @@ "Step 1: Processing data": "Passaggio 1: elaborazione dei dati", "Step 3a: Model training started": "Passaggio 3a: è iniziato l'addestramento del modello", "Stop audio conversion": "Arresta la conversione audio", - "Successfully built index into": "成功构建索引到", - "Takeover WASAPI device": "独占 WASAPI 设备", + "Successfully built index into": "Successfully built index into", + "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "Frequenza di campionamento target:", - "The audio file to be processed": "待处理音频文件", + "The audio file to be processed": "The audio file to be processed", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "Questo software è open source con licenza MIT.
Se non si accetta questa clausola, non è possibile utilizzare o fare riferimento a codici e file all'interno del pacchetto software. Contratto-LICENZA.txt per dettagli.", "Total training epochs (total_epoch)": "Epoch totali di addestramento (total_epoch):", "Train": "Addestramento", @@ -153,7 +153,7 @@ "Whether the model has pitch guidance (required for singing, optional for speech)": "Se il modello ha una guida del tono (necessario per il canto, facoltativo per il parlato):", "Yes": "SÌ", "ckpt Processing": "Elaborazione ckpt", - "index path cannot contain unicode characters": "index文件路径不可包含中文", + "index path cannot contain unicode characters": "index path cannot contain unicode characters", "pth path cannot contain unicode characters": "pth è un'app per il futuro", - "step2:Pitch extraction & feature extraction": "step2:正在提取音高&正在提取特征" + "step2:Pitch extraction & feature extraction": "step2:Pitch extraction & feature extraction" } diff --git a/i18n/locale/ko_KR.json b/i18n/locale/ko_KR.json index cc975be..ff307ad 100644 --- a/i18n/locale/ko_KR.json +++ b/i18n/locale/ko_KR.json @@ -1,14 +1,14 @@ { "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### 모델 추출\n> logs 폴더 아래의 큰 파일 모델 경로 입력\n\n훈련 중간에 중단한 모델의 자동 추출 및 소형 파일 모델 저장이 안 되거나 중간 모델을 테스트하고 싶은 경우에 적합", - "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", + "### Model fusion\nCan be used to test timbre fusion.": "### 모델 융합\n음색 융합 테스트에 사용 가능", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### 모델 정보 수정\n> 오직 weights 폴더 아래에서 추출된 작은 모델 파일만 지원", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", - "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", - "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. 실험 구성 작성\n실험 데이터는 logs에 저장, 각 실험은 하나의 폴더, 수동으로 실험 이름 경로 입력 필요, 실험 구성, 로그, 훈련된 모델 파일 포함.", + "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.", + "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Step 3. Start training.\nFill in the training settings and start training the model and index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### 모델 정보 보기\n> 오직 weights 폴더에서 추출된 소형 모델 파일만 지원", - "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", - "Actually calculated": "实际计算", + "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).", + "Actually calculated": "Actually calculated", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "입력 소스 볼륨 엔벨로프와 출력 볼륨 엔벨로프의 결합 비율 입력, 1에 가까울수록 출력 엔벨로프 사용", "Algorithmic delays (ms)": "알고리즘 지연(ms)", "All processes have been completed!": "전체 과정 완료!", @@ -47,11 +47,11 @@ "Fusion": "융합", "GPU Information": "그래픽 카드 정보", "General settings": "일반 설정", - "Hidden": "不显示", - "ID of model A (long)": "A模型ID(长)", - "ID of model B (long)": "B模型ID(长)", - "ID(long)": "ID(long)", - "ID(short)": "ID(短)", + "Hidden": "Hidden", + "ID of model A (long)": "ID of model A (long)", + "ID of model B (long)": "ID of model B (long)", + "ID(long)": "ID (long)", + "ID(short)": "ID (short)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": ">=3인 경우 harvest 피치 인식 결과에 중간값 필터 적용, 필터 반경은 값으로 지정, 사용 시 무성음 감소 가능", "Inference time (ms)": "추론 시간 (ms)", "Inferencing voice": "추론 음색", @@ -59,25 +59,25 @@ "Input device": "입력 장치", "Input noise reduction": "입력 노이즈 감소", "Input voice monitor": "입력 모니터링", - "Link index to outside folder": "链接索引到外部", + "Link index to outside folder": "Link index to outside folder", "Load model": "모델 로드", "Load pre-trained base model D path": "미리 훈련된 베이스 모델 D 경로 로드", "Load pre-trained base model G path": "미리 훈련된 베이스 모델 G 경로 로드", "Loudness factor": "음량 인자", "Model": "모델", - "Model Author": "模型作者", - "Model Author (Nullable)": "模型作者(可空)", + "Model Author": "Model Author", + "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "모델 추론", "Model architecture version": "모델 버전 및 모델", "Model info": "모델 정보", "Model information to be modified": "변경할 모델 정보", "Model information to be placed": "삽입할 모델 정보", - "Model name": "模型名", + "Model name": "Model name", "Modify": "수정", "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "여러 오디오 파일을 일괄 입력할 수도 있음, 둘 중 하나 선택, 폴더 우선 읽기", "No": "아니오", "None": "None", - "Not exist": "无", + "Not exist": "Not exist", "Number of CPU processes used for harvest pitch algorithm": "harvest 프로세스 수", "Number of CPU processes used for pitch extraction and data processing": "음높이 추출 및 데이터 처리에 사용되는 CPU 프로세스 수", "One-click training": "원클릭 훈련", @@ -113,15 +113,15 @@ "Save name": "저장 이름", "Save only the latest '.ckpt' file to save disk space": "디스크 공간을 절약하기 위해 최신 ckpt 파일만 저장할지 여부", "Saved model name (without extension)": "저장된 모델명은 접미사 없음", - "Sealing date": "封装时间", + "Sealing date": "Sealing date", "Search feature ratio (controls accent strength, too high has artifacting)": "검색 특징 비율", "Select Speaker/Singer ID": "화자 ID 선택", "Select the .index file": ".index 파일 선택", "Select the .pth file": ".pth 파일 선택", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "음높이 추출 알고리즘 선택, 노래 입력 시 pm으로 속도 향상, harvest는 저음이 좋지만 매우 느림, crepe는 효과가 좋지만 GPU 사용, rmvpe는 효과가 가장 좋으며 GPU를 적게 사용", "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "음높이 추출 알고리즘 선택: 노래 입력 시 pm으로 속도 향상, 고품질 음성에는 CPU가 부족할 때 dio 사용, harvest는 품질이 더 좋지만 느림, rmvpe는 효과가 가장 좋으며 CPU/GPU를 적게 사용", - "Similarity": "相似度", - "Similarity (from 0 to 1)": "相似度(0到1)", + "Similarity": "Similarity", + "Similarity (from 0 to 1)": "Similarity (from 0 to 1)", "Single inference": "단일 추론", "Specify output folder": "출력 파일 폴더 지정", "Specify the output folder for accompaniment": "주된 목소리가 아닌 출력 폴더 지정", @@ -130,10 +130,10 @@ "Step 1: Processing data": "step1: 데이터 처리 중", "Step 3a: Model training started": "step3a: 모델 훈련 중", "Stop audio conversion": "오디오 변환 중지", - "Successfully built index into": "成功构建索引到", - "Takeover WASAPI device": "独占 WASAPI 设备", + "Successfully built index into": "Successfully built index into", + "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "목표 샘플링률", - "The audio file to be processed": "待处理音频文件", + "The audio file to be processed": "The audio file to be processed", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "이 소프트웨어는 MIT 라이선스로 공개되며, 저자는 소프트웨어에 대해 어떠한 통제권도 가지지 않습니다. 모든 귀책사유는 소프트웨어 사용자 및 소프트웨어에서 생성된 결과물을 사용하는 당사자에게 있습니다.
해당 조항을 인정하지 않는 경우, 소프트웨어 패키지의 어떠한 코드나 파일도 사용하거나 인용할 수 없습니다. 자세한 내용은 루트 디렉토리의 LICENSE를 참조하세요.", "Total training epochs (total_epoch)": "총 훈련 라운드 수 total_epoch", "Train": "훈련", diff --git a/i18n/locale/pt_BR.json b/i18n/locale/pt_BR.json index d8a3f7c..0559f6a 100644 --- a/i18n/locale/pt_BR.json +++ b/i18n/locale/pt_BR.json @@ -3,16 +3,16 @@ "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Extração do modelo\n> Insira o caminho do modelo de arquivo grande na pasta 'logs'.\n\nIsso é útil se você quiser interromper o treinamento no meio do caminho e extrair e salvar manualmente um arquivo de modelo pequeno, ou se quiser testar um modelo intermediário.", "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Modificar informações do modelo\n> Suportado apenas para arquivos de modelo pequenos extraídos da pasta 'weights'.", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", - "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", - "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Etapa 1. Preencha a configuração experimental.\nOs dados experimentais são armazenados na pasta 'logs', com cada experimento tendo uma pasta separada. Digite manualmente o caminho do nome do experimento, que contém a configuração experimental, os logs e os arquivos de modelo treinados.", + "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.", + "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Step 3. Start training.\nFill in the training settings and start training the model and index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Exibir informações do modelo\n> Suportado apenas para arquivos de modelo pequenos extraídos da pasta 'weights'.", - "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", - "Actually calculated": "实际计算", + "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).", + "Actually calculated": "Actually calculated", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "O envelope de volume da fonte de entrada substitui a taxa de fusão do envelope de volume de saída, quanto mais próximo de 1, mais o envelope de saída é usado:", "Algorithmic delays (ms)": "Atrasos algorítmicos (ms)", "All processes have been completed!": "Todos os processos foram concluídos!", - "Audio device": "音频设备", + "Audio device": "Audio device", "Auto-detect index path and select from the dropdown": "Detecte automaticamente o caminho do Index e selecione no menu suspenso:", "Batch conversion. Enter the folder containing the audio files to be converted or upload multiple audio files. The converted audio will be output in the specified folder (default: 'opt').": "Conversão em Massa.", "Batch inference": "Conversão em Lote", @@ -20,18 +20,18 @@ "Batch size per GPU": "Batch Size (DEIXE COMO ESTÁ a menos que saiba o que está fazendo, no Colab pode deixar até 20!):", "Cache all training sets to GPU memory. Caching small datasets (less than 10 minutes) can speed up training, but caching large datasets will consume a lot of GPU memory and may not provide much speed improvement": "Se deve armazenar em cache todos os conjuntos de treinamento na memória de vídeo. Pequenos dados com menos de 10 minutos podem ser armazenados em cache para acelerar o treinamento, e um cache de dados grande irá explodir a memória de vídeo e não aumentar muito a velocidade:", "Calculate": "计算", - "Choose sample rate of the device": "使用设备采样率", - "Choose sample rate of the model": "使用模型采样率", + "Choose sample rate of the device": "Choose sample rate of the device", + "Choose sample rate of the model": "Choose sample rate of the model", "Convert": "Converter", - "Device type": "设备类型", - "Enable phase vocoder": "启用相位声码器", + "Device type": "Device type", + "Enable phase vocoder": "Enable phase vocoder", "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "Configuração do número do cartão rmvpe: Use - para separar os números dos cartões de entrada de diferentes processos. Por exemplo, 0-0-1 é usado para executar 2 processos no cartão 0 e 1 processo no cartão 1.", "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2": "Digite o (s) índice(s) da GPU separados por '-', por exemplo, 0-1-2 para usar a GPU 0, 1 e 2:", "Enter the experiment name": "Nome da voz:", "Enter the path of the audio folder to be processed": "Caminho da pasta de áudio a ser processada:", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "Caminho da pasta de áudio a ser processada (copie-o da barra de endereços do gerenciador de arquivos):", "Enter the path of the training folder": "Caminho da pasta de treinamento:", - "Exist": "有", + "Exist": "Exist", "Export Onnx": "Exportar Onnx", "Export Onnx Model": "Exportar Modelo Onnx", "Export audio (click on the three dots in the lower right corner to download)": "Exportar áudio (clique nos três pontos no canto inferior direito para baixar)", @@ -50,8 +50,8 @@ "Hidden": "不显示", "ID of model A (long)": "A模型ID(长)", "ID of model B (long)": "B模型ID(长)", - "ID(long)": "ID(long)", - "ID(short)": "ID(短)", + "ID(long)": "ID (long)", + "ID(short)": "ID (short)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": ">=3, use o filtro mediano para o resultado do reconhecimento do tom da heverst, e o valor é o raio do filtro, que pode enfraquecer o mudo.", "Inference time (ms)": "Tempo de inferência (ms)", "Inferencing voice": "Escolha o seu Modelo:", @@ -59,25 +59,25 @@ "Input device": "Dispositivo de entrada", "Input noise reduction": "Redução de ruído de entrada", "Input voice monitor": "Monitoramento de entrada", - "Link index to outside folder": "链接索引到外部", + "Link index to outside folder": "Link index to outside folder", "Load model": "Modelo", "Load pre-trained base model D path": "Carregue o caminho D do modelo base pré-treinado:", "Load pre-trained base model G path": "Carregue o caminho G do modelo base pré-treinado:", "Loudness factor": "Fator de volume", "Model": "Modelo", - "Model Author": "模型作者", - "Model Author (Nullable)": "模型作者(可空)", + "Model Author": "Model Author", + "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "Inference", "Model architecture version": "Versão:", - "Model info": "模型信息", + "Model info": "Model info", "Model information to be modified": "Informações do modelo a ser modificado:", "Model information to be placed": "Informações do modelo a ser colocado:", - "Model name": "模型名", + "Model name": "Model name", "Modify": "Editar", "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "Você também pode inserir arquivos de áudio em lotes. Escolha uma das duas opções. É dada prioridade à leitura da pasta.", "No": "Não", "None": "None", - "Not exist": "无", + "Not exist": "Not exist", "Number of CPU processes used for harvest pitch algorithm": "Número de processos harvest", "Number of CPU processes used for pitch extraction and data processing": "Número de processos de CPU usados para extração de tom e processamento de dados:", "One-click training": "Treinamento com um clique", @@ -92,7 +92,7 @@ "Path to the feature index file. Leave blank to use the selected result from the dropdown": "Caminho para o arquivo de Index. Deixe em branco para usar o resultado selecionado no menu debaixo:", "Performance settings": "Configurações de desempenho.", "Pitch detection algorithm": "Algoritmo de detecção de pitch", - "Pitch guidance (f0)": "音高引导(f0)", + "Pitch guidance (f0)": "Pitch guidance (f0)", "Pitch settings": "Configurações de tom", "Please choose the .index file": "Selecione o arquivo de Index", "Please choose the .pth file": "Selecione o arquivo pth", @@ -100,13 +100,13 @@ "Process data": "Processar o Conjunto de Dados", "Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy": "Proteja consoantes sem voz e sons respiratórios, evite artefatos como quebra de som eletrônico e desligue-o quando estiver cheio de 0,5. Diminua-o para aumentar a proteção, mas pode reduzir o efeito de indexação:", "RVC Model Path": "Caminho do Modelo RVC:", - "Read from model": "从模型中读取", + "Read from model": "Read from model", "Refresh voice list and index path": "Atualizar lista de voz e caminho do Index", "Reload device list": "Recarregar lista de dispositivos", "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "Reamostragem pós-processamento para a taxa de amostragem final, 0 significa sem reamostragem:", "Response threshold": "Limiar de resposta", "Sample length": "Comprimento da Amostra", - "Sampling rate": "采样率", + "Sampling rate": "Sampling rate", "Save a small final model to the 'weights' folder at each save point": "Salve um pequeno modelo final na pasta 'weights' em cada ponto de salvamento:", "Save file name (default: same as the source file)": "Salvar nome do arquivo (padrão: igual ao arquivo de origem):", "Save frequency (save_every_epoch)": "Faça backup a cada # de Epoch:", @@ -120,8 +120,8 @@ "Select the .pth file": "Selecione o Arquivo", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "Selecione o algoritmo de extração de tom \n'pm': extração mais rápida, mas discurso de qualidade inferior; \n'harvest': graves melhores, mas extremamente lentos; \n'harvest': melhor qualidade, mas extração mais lenta); 'crepe': melhor qualidade, mas intensivo em GPU; 'magio-crepe': melhor opção; 'RMVPE': um modelo robusto para estimativa de afinação vocal em música polifônica;", "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "Selecione o algoritmo de extração de tom \n'pm': extração mais rápida, mas discurso de qualidade inferior; \n'harvest': graves melhores, mas extremamente lentos; \n'crepe': melhor qualidade (mas intensivo em GPU);\n rmvpe tem o melhor efeito e consome menos CPU/GPU.", - "Similarity": "相似度", - "Similarity (from 0 to 1)": "相似度(0到1)", + "Similarity": "Similarity", + "Similarity (from 0 to 1)": "Similarity (from 0 to 1)", "Single inference": "Único", "Specify output folder": "Especifique a pasta de saída:", "Specify the output folder for accompaniment": "Informar a pasta de saída para acompanhamento:", @@ -130,10 +130,10 @@ "Step 1: Processing data": "Etapa 1: Processamento de dados", "Step 3a: Model training started": "Etapa 3a: Treinamento do modelo iniciado", "Stop audio conversion": "Conversão de áudio", - "Successfully built index into": "成功构建索引到", - "Takeover WASAPI device": "独占 WASAPI 设备", + "Successfully built index into": "Successfully built index into", + "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "Taxa de amostragem:", - "The audio file to be processed": "待处理音频文件", + "The audio file to be processed": "The audio file to be processed", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "
The Mangio-RVC 💻 | Tradução por Krisp e Rafael Godoy Ebert | AI HUB BRASIL
Este software é de código aberto sob a licença MIT. O autor não tem qualquer controle sobre o software. Aqueles que usam o software e divulgam os sons exportados pelo software são totalmente responsáveis.
Se você não concorda com este termo, você não pode usar ou citar nenhum código e arquivo no pacote de software. Para obter detalhes, consulte o diretório raiz O acordo a ser seguido para uso LICENSE
", "Total training epochs (total_epoch)": "Número total de ciclos(epoch) de treino (se escolher um valor alto demais, o seu modelo parecerá terrivelmente sobretreinado):", "Train": "Treinar", @@ -155,5 +155,5 @@ "ckpt Processing": "processamento ckpt", "index path cannot contain unicode characters": "O caminho do arquivo de Index não pode conter caracteres chineses", "pth path cannot contain unicode characters": "o caminho do arquivo pth não pode conter caracteres chineses", - "step2:Pitch extraction & feature extraction": "step2:正在提取音高&正在提取特征" + "step2:Pitch extraction & feature extraction": "step2:Pitch extraction & feature extraction" } diff --git a/i18n/locale/ru_RU.json b/i18n/locale/ru_RU.json index a141796..3aa0f33 100644 --- a/i18n/locale/ru_RU.json +++ b/i18n/locale/ru_RU.json @@ -1,37 +1,37 @@ { "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Создание модели из данных\n> Полученных в процессе обучения (введите путь к большому файлу модели в папке 'logs').\n\nМожет пригодиться, если вам нужно завершить обучение и получить маленький файл готовой модели, или если вам нужно проверить недообученную модель.", - "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", + "### Model fusion\nCan be used to test timbre fusion.": "### Слияние моделей> Может быть использовано для проверки слияния тембра.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Изменить информацию о модели\n> Работает только с маленькими моделями, взятыми из папки 'weights'.", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", - "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", - "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Шаг 1. Конфигурирование модели.\nДанные обучения модели сохраняются в папку 'logs', и для каждой модели создаётся отдельная папка. Введите вручную путь к настройкам для модели, в которой находятся логи и тренировочные файлы.", + "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.", + "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Step 3. Start training.\nFill in the training settings and start training the model and index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Просмотреть информацию о модели\n> Работает только с маленькими моделями, взятыми из папки 'weights'.", - "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", - "Actually calculated": "实际计算", + "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).", + "Actually calculated": "Actually calculated", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "Использовать громкость входного файла для замены или перемешивания с громкостью выходного файла. Чем ближе соотношение к 1, тем больше используется звука из выходного файла:", - "Algorithmic delays (ms)": "算法延迟(ms)", + "Algorithmic delays (ms)": "Algorithmic delays (ms)", "All processes have been completed!": "Все процессы завершены!", "Audio device": "Аудиоустройство", "Auto-detect index path and select from the dropdown": "Автоматически найденные файлы индексов черт (выберите вариант из списка):", "Batch conversion. Enter the folder containing the audio files to be converted or upload multiple audio files. The converted audio will be output in the specified folder (default: 'opt').": "Массовое преобразование. Введите путь к папке, в которой находятся файлы для преобразования голоса или выгрузите несколько аудиофайлов. Сконвертированные файлы будут сохранены в указанной папке (по умолчанию: 'opt').", - "Batch inference": "批量推理", + "Batch inference": "Batch inference", "Batch processing for vocal accompaniment separation using the UVR5 model.
Example of a valid folder path format: D:\\path\\to\\input\\folder (copy it from the file manager address bar).
The model is divided into three categories:
1. Preserve vocals: Choose this option for audio without harmonies. It preserves vocals better than HP5. It includes two built-in models: HP2 and HP3. HP3 may slightly leak accompaniment but preserves vocals slightly better than HP2.
2. Preserve main vocals only: Choose this option for audio with harmonies. It may weaken the main vocals. It includes one built-in model: HP5.
3. De-reverb and de-delay models (by FoxJoy):
  (1) MDX-Net: The best choice for stereo reverb removal but cannot remove mono reverb;
 (234) DeEcho: Removes delay effects. Aggressive mode removes more thoroughly than Normal mode. DeReverb additionally removes reverb and can remove mono reverb, but not very effectively for heavily reverberated high-frequency content.
De-reverb/de-delay notes:
1. The processing time for the DeEcho-DeReverb model is approximately twice as long as the other two DeEcho models.
2. The MDX-Net-Dereverb model is quite slow.
3. The recommended cleanest configuration is to apply MDX-Net first and then DeEcho-Aggressive.": "Пакетная обработка для разделения вокального сопровождения с использованием модели UVR5.
Пример допустимого формата пути к папке: D:\\path\\to\\input\\folder
Модель разделена на три категории:
1. Сохранить вокал: выберите этот вариант для звука без гармоний. Он сохраняет вокал лучше, чем HP5. Он включает в себя две встроенные модели: HP2 и HP3. HP3 может немного пропускать инструментал, но сохраняет вокал немного лучше, чем HP2.
2. Сохранить только основной вокал: выберите этот вариант для звука с гармониями. Это может ослабить основной вокал. Он включает одну встроенную модель: HP5.
3. Модели удаления реверберации и задержки (от FoxJoy):
  (1) MDX-Net: лучший выбор для удаления стереореверберации, но он не может удалить монореверберацию;
 (234) DeEcho: удаляет эффекты задержки. Агрессивный режим удаляет более тщательно, чем Нормальный режим. DeReverb дополнительно удаляет реверберацию и может удалять монореверберацию, но не очень эффективно для сильно реверберированного высокочастотного контента.
Примечания по удалению реверберации/задержки:
1. Время обработки для модели DeEcho-DeReverb примерно в два раза больше, чем для двух других моделей DeEcho.
2. Модель MDX-Net-Dereverb довольно медленная.
3. Рекомендуемая самая чистая конфигурация — сначала применить MDX-Net, а затем DeEcho-Aggressive.", "Batch size per GPU": "Размер пачки для GPU:", "Cache all training sets to GPU memory. Caching small datasets (less than 10 minutes) can speed up training, but caching large datasets will consume a lot of GPU memory and may not provide much speed improvement": "Кэшировать все тренировочные сеты в видеопамять. Кэширование маленький датасетов (меньше 10 минут) может ускорить тренировку, но кэширование больших, наоборот, займёт много видеопамяти и не сильно ускорит тренировку:", - "Calculate": "计算", - "Choose sample rate of the device": "使用设备采样率", - "Choose sample rate of the model": "使用模型采样率", + "Calculate": "Calculate", + "Choose sample rate of the device": "Choose sample rate of the device", + "Choose sample rate of the model": "Choose sample rate of the model", "Convert": "Преобразовать", - "Device type": "设备类型", - "Enable phase vocoder": "启用相位声码器", + "Device type": "Device type", + "Enable phase vocoder": "Enable phase vocoder", "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "Введите номера графических процессоров, разделенные символом «-», например, 0-0-1, чтобы запустить два процесса на GPU 0 и один процесс на GPU 1:", "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2": "Введите, какие(-ую) GPU(-у) хотите использовать через '-', например 0-1-2, чтобы использовать GPU с номерами 0, 1 и 2:", "Enter the experiment name": "Название модели:", "Enter the path of the audio folder to be processed": "Путь к папке с аудиофайлами для обработки:", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "Путь к папке с аудиофайлами для переработки (можно скопировать путь из адресной строки файлового менеджера):", "Enter the path of the training folder": "Путь к папке с аудиозаписями, на которых будет обучаться модель:", - "Exist": "有", + "Exist": "Exist", "Export Onnx": "Экспорт ONNX", "Export Onnx Model": "Экспортировать модель", "Export audio (click on the three dots in the lower right corner to download)": "Аудиофайл (чтобы скачать, нажмите на три точки справа в плеере)", @@ -47,42 +47,42 @@ "Fusion": "Запустить слияние", "GPU Information": "Информация о графических процессорах (GPUs):", "General settings": "Основные настройки", - "Hidden": "不显示", - "ID of model A (long)": "A模型ID(长)", - "ID of model B (long)": "B模型ID(长)", - "ID(long)": "ID(long)", - "ID(short)": "ID(短)", + "Hidden": "Hidden", + "ID of model A (long)": "ID of model A (long)", + "ID of model B (long)": "ID of model B (long)", + "ID(long)": "ID (long)", + "ID(short)": "ID (short)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": "Если значение больше 3: применить медианную фильтрацию к вытащенным тональностям. Значение контролирует радиус фильтра и может уменьшить излишнее дыхание.", "Inference time (ms)": "Время переработки (мс)", "Inferencing voice": "Желаемый голос:", - "Information": "信息", + "Information": "Information", "Input device": "Входное устройство", "Input noise reduction": "Уменьшение входного шума", - "Input voice monitor": "输入监听", - "Link index to outside folder": "链接索引到外部", + "Input voice monitor": "Input voice monitor", + "Link index to outside folder": "Link index to outside folder", "Load model": "Загрузить модель", "Load pre-trained base model D path": "Путь к предварительно обученной базовой модели D:", "Load pre-trained base model G path": "Путь к предварительно обученной базовой модели G:", "Loudness factor": "коэффициент громкости", "Model": "Модели", - "Model Author": "模型作者", - "Model Author (Nullable)": "模型作者(可空)", + "Model Author": "Model Author", + "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "Изменение голоса", "Model architecture version": "Версия архитектуры модели:", - "Model info": "模型信息", + "Model info": "Model info", "Model information to be modified": "Информация, которая будет изменена:", "Model information to be placed": "Информация о модели:", - "Model name": "模型名", + "Model name": "Model name", "Modify": "Изменить", "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "Можно также импортировать несколько аудиофайлов. Если путь к папке существует, то этот ввод игнорируется.", "No": "Нет", "None": "None", - "Not exist": "无", + "Not exist": "Not exist", "Number of CPU processes used for harvest pitch algorithm": "Количество процессор harvest", "Number of CPU processes used for pitch extraction and data processing": "Число процессов ЦП, используемое для оценки высоты голоса и обработки данных:", "One-click training": "Обучение в одно нажатие", "Onnx Export Path": "Путь для сохранения модели в формате ONNX:", - "Output converted voice": "输出变声", + "Output converted voice": "Output converted voice", "Output device": "Выходное устройство", "Output information": "Статистика", "Output noise reduction": "Уменьшение выходного шума", @@ -92,7 +92,7 @@ "Path to the feature index file. Leave blank to use the selected result from the dropdown": "Путь к файлу индекса черт. Оставьте пустым, чтобы использовать выбранный вариант из списка ниже:", "Performance settings": "Настройки быстроты", "Pitch detection algorithm": "Алгоритм оценки высоты звука", - "Pitch guidance (f0)": "音高引导(f0)", + "Pitch guidance (f0)": "Pitch guidance (f0)", "Pitch settings": "Настройка высоты звука", "Please choose the .index file": "Пожалуйста, выберите файл индекса", "Please choose the .pth file": "Пожалуйста, выберите файл pth", @@ -100,29 +100,29 @@ "Process data": "Обработать данные", "Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy": "Защитить глухие согласные и звуки дыхания для предотвращения артефактов, например, разрывания в электронной музыке. Поставьте на 0.5, чтобы выключить. Уменьшите значение для повышения защиты, но учтите, что при этом может ухудшиться точность индексирования:", "RVC Model Path": "Путь к модели RVC:", - "Read from model": "从模型中读取", + "Read from model": "Read from model", "Refresh voice list and index path": "Обновить список голосов и индексов", "Reload device list": "Обновить список устройств", "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "Изменить частоту дискретизации в выходном файле на финальную. Поставьте 0, чтобы ничего не изменялось:", "Response threshold": "Порог ответа", "Sample length": "Длина сэмпла", - "Sampling rate": "采样率", + "Sampling rate": "Sampling rate", "Save a small final model to the 'weights' folder at each save point": "Сохранять маленькую финальную модель в папку 'weights' на каждой точке сохранения:", "Save file name (default: same as the source file)": "Название сохранённого файла (по умолчанию: такое же, как и у входного):", "Save frequency (save_every_epoch)": "Частота сохранения (save_every_epoch):", "Save name": "Имя файла для сохранения:", "Save only the latest '.ckpt' file to save disk space": "Сохранять только последний файл '.ckpt', чтобы сохранить место на диске:", "Saved model name (without extension)": "Имя файла модели для сохранения (без расширения):", - "Sealing date": "封装时间", + "Sealing date": "Sealing date", "Search feature ratio (controls accent strength, too high has artifacting)": "Соотношение поиска черт:", "Select Speaker/Singer ID": "Номер говорящего:", "Select the .index file": "Выбрать файл .index", "Select the .pth file": "Выбрать файл .pth", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "Выберите алгоритм оценки высоты голоса ('pm': работает быстро, но даёт низкое качество речи; 'harvest': басы лучше, но работает очень медленно; 'crepe': лучшее качество, но сильно нагружает GPU; 'rmvpe': лучшее качество и минимальная нагрузка на GPU):", - "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU", - "Similarity": "相似度", - "Similarity (from 0 to 1)": "相似度(0到1)", - "Single inference": "单次推理", + "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU", + "Similarity": "Similarity", + "Similarity (from 0 to 1)": "Similarity (from 0 to 1)", + "Single inference": "Single inference", "Specify output folder": "Папка для результатов:", "Specify the output folder for accompaniment": "Путь к папке для сохранения аккомпанемента:", "Specify the output folder for vocals": "Путь к папке для сохранения вокала:", @@ -130,10 +130,10 @@ "Step 1: Processing data": "Шаг 1. Переработка данных", "Step 3a: Model training started": "Шаг 3. Запуск обучения модели", "Stop audio conversion": "Закончить конвертацию аудио", - "Successfully built index into": "成功构建索引到", - "Takeover WASAPI device": "独占 WASAPI 设备", + "Successfully built index into": "Successfully built index into", + "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "Частота дискретизации аудио:", - "The audio file to be processed": "待处理音频文件", + "The audio file to be processed": "The audio file to be processed", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "Это программное обеспечение с открытым исходным кодом распространяется по лицензии MIT. Автор никак не контролирует это программное обеспечение. Пользователи, которые используют эту программу и распространяют аудиозаписи, полученные с помощью этой программы, несут полную ответственность за это. Если вы не согласны с этим, вы не можете использовать какие-либо коды и файлы в рамках этой программы или ссылаться на них. Подробнее в файле Agreement-LICENSE.txt в корневом каталоге программы.", "Total training epochs (total_epoch)": "Полное количество эпох (total_epoch):", "Train": "Обучение модели", @@ -155,5 +155,5 @@ "ckpt Processing": "Обработка ckpt", "index path cannot contain unicode characters": "Путь к файлу индекса", "pth path cannot contain unicode characters": "Путь к файлу pth", - "step2:Pitch extraction & feature extraction": "step2:正在提取音高&正在提取特征" + "step2:Pitch extraction & feature extraction": "step2:Pitch extraction & feature extraction" } diff --git a/i18n/locale/tr_TR.json b/i18n/locale/tr_TR.json index 4a8ad0b..74914be 100644 --- a/i18n/locale/tr_TR.json +++ b/i18n/locale/tr_TR.json @@ -3,35 +3,35 @@ "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### Model çıkartma\n> Büyük dosya modeli yolunu 'logs' klasöründe girin.\n\nBu, eğitimi yarıda bırakmak istediğinizde ve manuel olarak küçük bir model dosyası çıkartmak ve kaydetmek istediğinizde veya bir ara modeli test etmek istediğinizde kullanışlıdır.", "### Model fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Model bilgilerini düzenle\n> Sadece 'weights' klasöründen çıkarılan küçük model dosyaları desteklenir.", - "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", - "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", - "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", + "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Adım 1. Deneysel yapılandırmayı doldurun.\nDeneysel veriler 'logs' klasöründe saklanır ve her bir deney için ayrı bir klasör vardır. Deneysel adı yolu manuel olarak girin; bu yol, deneysel yapılandırmayı, günlükleri ve eğitilmiş model dosyalarını içerir.", + "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.", + "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### Step 3. Start training.\nFill in the training settings and start training the model and index.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### Model bilgilerini görüntüle\n> Sadece 'weights' klasöründen çıkarılan küçük model dosyaları desteklenir.", - "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", - "Actually calculated": "实际计算", + "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).", + "Actually calculated": "Actually calculated", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "Sesin hacim zarfını ayarlayın. 0'a yakın değerler, sesin orijinal vokallerin hacmine benzer olmasını sağlar. Düşük bir değerle ses gürültüsünü maskeleyebilir ve hacmi daha doğal bir şekilde duyulabilir hale getirebilirsiniz. 1'e yaklaştıkça sürekli bir yüksek ses seviyesi elde edilir:", "Algorithmic delays (ms)": "算法延迟(ms)", "All processes have been completed!": "Tüm işlemler tamamlandı!", "Audio device": "Ses cihazı", "Auto-detect index path and select from the dropdown": "İndeks yolunu otomatik olarak tespit et ve açılır menüden seçim yap.", "Batch conversion. Enter the folder containing the audio files to be converted or upload multiple audio files. The converted audio will be output in the specified folder (default: 'opt').": "Toplu dönüştür. Dönüştürülecek ses dosyalarının bulunduğu klasörü girin veya birden çok ses dosyasını yükleyin. Dönüştürülen ses dosyaları belirtilen klasöre ('opt' varsayılan olarak) dönüştürülecektir", - "Batch inference": "批量推理", + "Batch inference": "Batch inference", "Batch processing for vocal accompaniment separation using the UVR5 model.
Example of a valid folder path format: D:\\path\\to\\input\\folder (copy it from the file manager address bar).
The model is divided into three categories:
1. Preserve vocals: Choose this option for audio without harmonies. It preserves vocals better than HP5. It includes two built-in models: HP2 and HP3. HP3 may slightly leak accompaniment but preserves vocals slightly better than HP2.
2. Preserve main vocals only: Choose this option for audio with harmonies. It may weaken the main vocals. It includes one built-in model: HP5.
3. De-reverb and de-delay models (by FoxJoy):
  (1) MDX-Net: The best choice for stereo reverb removal but cannot remove mono reverb;
 (234) DeEcho: Removes delay effects. Aggressive mode removes more thoroughly than Normal mode. DeReverb additionally removes reverb and can remove mono reverb, but not very effectively for heavily reverberated high-frequency content.
De-reverb/de-delay notes:
1. The processing time for the DeEcho-DeReverb model is approximately twice as long as the other two DeEcho models.
2. The MDX-Net-Dereverb model is quite slow.
3. The recommended cleanest configuration is to apply MDX-Net first and then DeEcho-Aggressive.": "Batch işleme kullanarak vokal eşlik ayrımı için UVR5 modeli kullanılır.
Geçerli bir klasör yol formatı örneği: D:\\path\\to\\input\\folder (dosya yöneticisi adres çubuğundan kopyalanır).
Model üç kategoriye ayrılır:
1. Vokalleri koru: Bu seçeneği, harmoni içermeyen sesler için kullanın. HP5'ten daha iyi bir şekilde vokalleri korur. İki dahili model içerir: HP2 ve HP3. HP3, eşlik sesini hafifçe sızdırabilir, ancak vokalleri HP2'den biraz daha iyi korur.
2. Sadece ana vokalleri koru: Bu seçeneği, harmoni içeren sesler için kullanın. Ana vokalleri zayıflatabilir. Bir dahili model içerir: HP5.
3. Reverb ve gecikme modelleri (FoxJoy tarafından):
  (1) MDX-Net: Stereo reverb'i kaldırmak için en iyi seçenek, ancak mono reverb'i kaldıramaz;
 (234) DeEcho: Gecikme efektlerini kaldırır. Agresif mod, Normal moda göre daha kapsamlı bir şekilde kaldırma yapar. DeReverb ayrıca reverb'i kaldırır ve mono reverb'i kaldırabilir, ancak yoğun yankılı yüksek frekanslı içerikler için çok etkili değildir.
Reverb/gecikme notları:
1. DeEcho-DeReverb modelinin işleme süresi diğer iki DeEcho modeline göre yaklaşık olarak iki kat daha uzundur.
2. MDX-Net-Dereverb modeli oldukça yavaştır.
3. Tavsiye edilen en temiz yapılandırma önce MDX-Net'i uygulamak ve ardından DeEcho-Aggressive uygulamaktır.", "Batch size per GPU": "Her GPU için yığın boyutu (batch_size):", "Cache all training sets to GPU memory. Caching small datasets (less than 10 minutes) can speed up training, but caching large datasets will consume a lot of GPU memory and may not provide much speed improvement": "Tüm eğitim verilerini GPU belleğine önbelleğe alıp almayacağınızı belirtin. Küçük veri setlerini (10 dakikadan az) önbelleğe almak eğitimi hızlandırabilir, ancak büyük veri setlerini önbelleğe almak çok fazla GPU belleği tüketir ve çok fazla hız artışı sağlamaz:", - "Calculate": "计算", - "Choose sample rate of the device": "使用设备采样率", - "Choose sample rate of the model": "使用模型采样率", + "Calculate": "Calculate", + "Choose sample rate of the device": "Choose sample rate of the device", + "Choose sample rate of the model": "Choose sample rate of the model", "Convert": "Dönüştür", - "Device type": "设备类型", - "Enable phase vocoder": "启用相位声码器", - "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程", + "Device type": "Device type", + "Enable phase vocoder": "Enable phase vocoder", + "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1", "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2": "GPU indekslerini '-' ile ayırarak girin, örneğin 0-1-2, GPU 0, 1 ve 2'yi kullanmak için:", "Enter the experiment name": "Deneysel adı girin:", "Enter the path of the audio folder to be processed": "İşlenecek ses klasörünün yolunu girin:", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "İşlenecek ses klasörünün yolunu girin (dosya yöneticisinin adres çubuğundan kopyalayın):", "Enter the path of the training folder": "Eğitim klasörünün yolunu girin:", - "Exist": "有", + "Exist": "Exist", "Export Onnx": "Onnx Dışa Aktar", "Export Onnx Model": "Onnx Modeli Dışa Aktar", "Export audio (click on the three dots in the lower right corner to download)": "Ses dosyasını dışa aktar (indirmek için sağ alt köşedeki üç noktaya tıklayın)", @@ -41,44 +41,44 @@ "F0 curve file (optional). One pitch per line. Replaces the default F0 and pitch modulation": "F0 eğrisi dosyası (isteğe bağlı). Her satırda bir pitch değeri bulunur. Varsayılan F0 ve pitch modülasyonunu değiştirir:", "FAQ (Frequently Asked Questions)": "Sıkça Sorulan Sorular (SSS)", "Fade length": "Geçiş (Fade) uzunluğu", - "Fail": "失败", + "Fail": "Fail", "Feature extraction": "Özellik çıkartma", - "Formant offset": "共振偏移", + "Formant offset": "Formant offset", "Fusion": "Birleştir", "GPU Information": "GPU Bilgisi", "General settings": "Genel ayarlar", - "Hidden": "不显示", - "ID of model A (long)": "A模型ID(长)", - "ID of model B (long)": "B模型ID(长)", - "ID(long)": "ID(long)", - "ID(short)": "ID(短)", + "Hidden": "Hidden", + "ID of model A (long)": "ID of model A (long)", + "ID of model B (long)": "ID of model B (long)", + "ID(long)": "ID (long)", + "ID(short)": "ID (short)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": "Eğer >=3 ise, elde edilen pitch sonuçlarına median filtreleme uygula. Bu değer, filtre yarıçapını temsil eder ve nefesliliği azaltabilir.", "Inference time (ms)": "Çıkarsama süresi (ms)", "Inferencing voice": "Ses çıkartma (Inference):", - "Information": "信息", + "Information": "Information", "Input device": "Giriş cihazı", "Input noise reduction": "Giriş gürültü azaltma", - "Input voice monitor": "输入监听", - "Link index to outside folder": "链接索引到外部", + "Input voice monitor": "Input voice monitor", + "Link index to outside folder": "Link index to outside folder", "Load model": "Model yükle", "Load pre-trained base model D path": "Önceden eğitilmiş temel D modelini yükleme yolu:", "Load pre-trained base model G path": "Önceden eğitilmiş temel G modelini yükleme yolu:", "Loudness factor": "ses yüksekliği faktörü", "Model": "Model", - "Model Author": "模型作者", - "Model Author (Nullable)": "模型作者(可空)", + "Model Author": "Model Author", + "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "Model çıkartma (Inference)", "Model architecture version": "Model mimari versiyonu:", - "Model info": "模型信息", + "Model info": "Model info", "Model information to be modified": "Düzenlenecek model bilgileri:", "Model information to be placed": "Eklemek için model bilgileri:", - "Model name": "模型名", + "Model name": "Model name", "Modify": "Düzenle", "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "Ses dosyaları ayrıca toplu olarak, iki seçimle, öncelikli okuma klasörüyle içe aktarılabilir", "No": "Hayır", "None": "None", - "Not exist": "无", - "Number of CPU processes used for harvest pitch algorithm": "harvest进程数", + "Not exist": "Not exist", + "Number of CPU processes used for harvest pitch algorithm": "Number of CPU processes used for harvest pitch algorithm", "Number of CPU processes used for pitch extraction and data processing": "Ses yüksekliği çıkartmak (Pitch) ve verileri işlemek için kullanılacak CPU işlemci sayısı:", "One-click training": "Tek Tuşla Eğit", "Onnx Export Path": "Onnx Dışa Aktarım Yolu:", @@ -91,8 +91,8 @@ "Path to Model B": "B Modeli Yolu:", "Path to the feature index file. Leave blank to use the selected result from the dropdown": "Özellik indeksi dosyasının yolunu belirtin. Seçilen sonucu kullanmak için boş bırakın veya açılır menüden seçim yapın.", "Performance settings": "Performans ayarları", - "Pitch detection algorithm": "音高算法", - "Pitch guidance (f0)": "音高引导(f0)", + "Pitch detection algorithm": "Pitch detection algorithm", + "Pitch guidance (f0)": "Pitch guidance (f0)", "Pitch settings": "Pitch ayarları", "Please choose the .index file": "Lütfen .index dosyası seçin", "Please choose the .pth file": "Lütfen .pth dosyası seçin", @@ -106,23 +106,23 @@ "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "Son işleme aşamasında çıktı sesini son örnekleme hızına yeniden örnekle. 0 değeri için yeniden örnekleme yapılmaz:", "Response threshold": "Tepki eşiği", "Sample length": "Örnekleme uzunluğu", - "Sampling rate": "采样率", + "Sampling rate": "Sampling rate", "Save a small final model to the 'weights' folder at each save point": "Her kaydetme noktasında son küçük bir modeli 'weights' klasörüne kaydetmek için:", "Save file name (default: same as the source file)": "Kaydedilecek dosya adı (varsayılan: kaynak dosya ile aynı):", "Save frequency (save_every_epoch)": "Kaydetme sıklığı (save_every_epoch):", "Save name": "Kaydetme Adı:", "Save only the latest '.ckpt' file to save disk space": "Sadece en son '.ckpt' dosyasını kaydet:", "Saved model name (without extension)": "Kaydedilecek model adı (uzantı olmadan):", - "Sealing date": "封装时间", + "Sealing date": "Sealing date", "Search feature ratio (controls accent strength, too high has artifacting)": "Arama özelliği oranı (vurgu gücünü kontrol eder, çok yüksek olması sanal etkilere neden olur)", "Select Speaker/Singer ID": "Konuşmacı/Şarkıcı No seçin:", "Select the .index file": ".index dosyası seç", "Select the .pth file": ".pth dosyası seç", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "Pitch algoritmasını seçin ('pm': daha hızlı çıkarır ancak daha düşük kaliteli konuşma; 'harvest': daha iyi konuşma sesi ancak son derece yavaş; 'crepe': daha da iyi kalite ancak GPU yoğunluğu gerektirir):", - "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU", - "Similarity": "相似度", - "Similarity (from 0 to 1)": "相似度(0到1)", - "Single inference": "单次推理", + "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU", + "Similarity": "Similarity", + "Similarity (from 0 to 1)": "Similarity (from 0 to 1)", + "Single inference": "Single inference", "Specify output folder": "Çıkış klasörünü belirt:", "Specify the output folder for accompaniment": "Müzik ve diğer sesler için çıkış klasörünü belirtin:", "Specify the output folder for vocals": "Vokal için çıkış klasörünü belirtin:", @@ -130,10 +130,10 @@ "Step 1: Processing data": "Adım 1: Veri işleme", "Step 3a: Model training started": "Adım 3a: Model eğitimi başladı", "Stop audio conversion": "Ses dönüştürmeyi durdur", - "Successfully built index into": "成功构建索引到", - "Takeover WASAPI device": "独占 WASAPI 设备", + "Successfully built index into": "Successfully built index into", + "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "Hedef örnekleme oranı:", - "The audio file to be processed": "待处理音频文件", + "The audio file to be processed": "The audio file to be processed", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "Bu yazılım, MIT lisansı altında açık kaynaklıdır. Yazarın yazılım üzerinde herhangi bir kontrolü yoktur. Yazılımı kullanan ve yazılım tarafından dışa aktarılan sesleri dağıtan kullanıcılar sorumludur.
Eğer bu maddeyle aynı fikirde değilseniz, yazılım paketi içindeki herhangi bir kod veya dosyayı kullanamaz veya referans göremezsiniz. Detaylar için kök dizindeki Agreement-LICENSE.txt dosyasına bakınız.", "Total training epochs (total_epoch)": "Toplam eğitim turu (total_epoch):", "Train": "Eğitim", @@ -155,5 +155,5 @@ "ckpt Processing": "ckpt İşleme", "index path cannot contain unicode characters": ".index dosya yolu Çince karakter içeremez", "pth path cannot contain unicode characters": ".pth dosya yolu Çince karakter içeremez", - "step2:Pitch extraction & feature extraction": "step2:正在提取音高&正在提取特征" + "step2:Pitch extraction & feature extraction": "step2:Pitch extraction & feature extraction" }