{ "### 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.": "### 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 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.": "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.", "### 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.": "### 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.": "### View model information\n> Only supported for small model files extracted from the 'weights' folder.", "#### 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": "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", "Algorithmic delays (ms)": "Algorithmic delays (ms)", "All processes have been completed!": "All processes have been completed!", "Audio device": "Audio device", "Auto-detect index path and select from the dropdown": "Auto-detect index path and select from the dropdown", "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').": "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').", "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 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 size per GPU": "Batch size 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": "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", "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": "Convert", "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": "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2", "Enter the experiment name": "Enter the experiment name", "Enter the path of the audio folder to be processed": "Enter the path of the audio folder to be processed", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)", "Enter the path of the training folder": "Enter the path of the training folder", "Exist": "Exist", "Export Onnx": "Export Onnx", "Export Onnx Model": "Export Onnx Model", "Export audio (click on the three dots in the lower right corner to download)": "Export audio (click on the three dots in the lower right corner to download)", "Export file format": "Export file format", "Extra inference time": "Extra inference time", "Extract": "Extract", "F0 curve file (optional). One pitch per line. Replaces the default F0 and pitch modulation": "F0 curve file (optional). One pitch per line. Replaces the default F0 and pitch modulation", "FAQ (Frequently Asked Questions)": "FAQ (Frequently Asked Questions)", "Fade length": "Fade length", "Fail": "Fail", "Feature extraction": "Feature extraction", "Feature searching ratio": "Feature searching ratio", "Formant offset": "Formant offset", "Fusion": "Fusion", "GPU Information": "GPU Information", "General settings": "General settings", "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.": "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.", "Inference time (ms)": "Inference time (ms)", "Inferencing voice": "Inferencing voice", "Information": "Information", "Input device": "Input device", "Input noise reduction": "Input noise reduction", "Input voice monitor": "Input voice monitor", "Link index to outside folder": "Link index to outside folder", "Load model": "Load model", "Load pre-trained base model D path": "Load pre-trained base model D path", "Load pre-trained base model G path": "Load pre-trained base model G path", "Loudness factor": "Loudness factor", "Model": "Model", "Model Author": "Model Author", "Model Author (Nullable)": "Model Author (Nullable)", "Model Inference": "Model Inference", "Model architecture version": "Model architecture version", "Model info": "Model info", "Model information to be modified": "Model information to be modified", "Model information to be placed": "Model information to be placed", "Model name": "Model name", "Modify": "Modify", "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": "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": "Number of CPU processes used for pitch extraction and data processing", "One-click training": "One-click training", "Onnx Export Path": "Onnx Export Path", "Output converted voice": "Output converted voice", "Output device": "Output device", "Output information": "Output information", "Output noise reduction": "Output noise reduction", "Path to Model": "Path to Model", "Path to Model A": "Path to Model A", "Path to Model B": "Path to Model B", "Path to the feature index file. Leave blank to use the selected result from the dropdown": "Path to the feature index file. Leave blank to use the selected result from the dropdown", "Performance settings": "Performance settings", "Pitch detection algorithm": "Pitch detection algorithm", "Pitch guidance (f0)": "Pitch guidance (f0)", "Pitch settings": "Pitch settings", "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": "Please specify the speaker/singer ID", "Process data": "Process data", "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": "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", "RVC Model Path": "RVC Model Path", "Read from model": "Read from model", "Refresh voice list and index path": "Refresh voice list and index path", "Reload device list": "Reload device list", "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling", "Response threshold": "Response threshold", "Sample length": "Sample length", "Sampling rate": "Sampling rate", "Save a small final model to the 'weights' folder at each save point": "Save a small final model to the 'weights' folder at each save point", "Save file name (default: same as the source file)": "Save file name (default: same as the source file)", "Save frequency (save_every_epoch)": "Save frequency (save_every_epoch)", "Save name": "Save name", "Save only the latest '.ckpt' file to save disk space": "Save only the latest '.ckpt' file to save disk space", "Saved model name (without extension)": "Saved model name (without extension)", "Sealing date": "Sealing date", "Select Speaker/Singer ID": "Select Speaker/Singer ID", "Select the .index file": "Select the .index file", "Select the .pth file": "Select the .pth file", "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": "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", "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": "Specify output folder", "Specify the output folder for accompaniment": "Specify the output folder for accompaniment", "Specify the output folder for vocals": "Specify the output folder for vocals", "Start audio conversion": "Start audio conversion", "Step 1: Processing data": "Step 1: Processing data", "Step 3a: Model training started": "Step 3a: Model training started", "Stop audio conversion": "Stop audio conversion", "Successfully built index into": "Successfully built index into", "Takeover WASAPI device": "Takeover WASAPI device", "Target sample rate": "Target sample rate", "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.": "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.", "Total training epochs (total_epoch)": "Total training epochs (total_epoch)", "Train": "Train", "Train feature index": "Train feature index", "Train model": "Train model", "Training complete. You can check the training logs in the console or the 'train.log' file under the experiment folder.": "Training complete. You can check the training logs in the console or the 'train.log' file under the experiment folder.", "Transpose (integer, number of semitones, raise by an octave: 12, lower by an octave: -12)": "Transpose (integer, number of semitones, raise by an octave: 12, lower by an octave: -12)", "Unfortunately, there is no compatible GPU available to support your training.": "Unfortunately, there is no compatible GPU available to support your training.", "Unknown": "Unknown", "Unload model to save GPU memory": "Unload model to save GPU memory", "Version": "Version", "View": "View", "Vocals/Accompaniment Separation & Reverberation Removal": "Vocals/Accompaniment Separation & Reverberation Removal", "Weight (w) for Model A": "Weight (w) for Model A", "Whether the model has pitch guidance": "Whether the model has pitch guidance", "Whether the model has pitch guidance (1: yes, 0: no)": "Whether the model has pitch guidance (1: yes, 0: no)", "Whether the model has pitch guidance (required for singing, optional for speech)": "Whether the model has pitch guidance (required for singing, optional for speech)", "Yes": "Yes", "ckpt Processing": "ckpt Processing", "index path cannot contain unicode characters": "index path cannot contain unicode characters", "pth path cannot contain unicode characters": "pth path cannot contain unicode characters", "step2:Pitch extraction & feature extraction": "step2:Pitch extraction & feature extraction" }