{ "set_lang": "Display language set to {lang}.", "no_support_gpu": "Unfortunately, no compatible GPU is available to support your training.", "text": "text", "upload_success": "File {name} uploaded successfully.", "download_url": "Download from the link", "download_from_csv": "Download from the CSV model repository", "search_models": "Search models", "upload": "Upload", "option_not_valid": "Invalid option!", "list_model": "Model list", "success": "Completed!", "index": "index", "model": "model", "zip": "compress", "search": "search", "provide_file": "Please provide a valid {filename} file!", "start": "Starting {start}...", "not_found": "Not found {name}.", "found": "Found {results} results!", "download_music": "download music", "download": "download", "provide_url": "Please provide a url.", "provide_name_is_save": "Please provide a model name to save.", "not_support_url": "Your model url is not supported.", "error_occurred": "An error occurred: {e}.", "not_model": "The file you uploaded is not a model file!", "unable_analyze_model": "Unable to analyze the model!", "download_pretrain": "Downloading pre-trained model...", "provide_pretrain": "Please provide a pre-trained model url {dg}.", "provide_hubert": "Please provide a url to the embedding model.", "sr_not_same": "The sample rates of the two models are not the same.", "architectures_not_same": "Cannot merge models. The architectures are not the same.", "fushion_model": "model fusion", "model_fushion_info": "The model {name} is fused from {pth_1} and {pth_2} with a ratio of {ratio}.", "not_found_create_time": "Creation time not found.", "format_not_valid": "Invalid format.", "read_info": "Models trained on different applications may produce different information or may not be readable!", "epoch": "epoch.", "step": "step", "sr": "Sample rate", "f0": "pitch training", "version": "version.", "not_f0": "Pitch training not performed", "trained_f0": "Pitch training performed", "model_info": "Model Name: {model_name}\n\n Model Creator: {model_author}\n\nEpoch: {epochs}\n\nSteps: {steps}\n\nVersion: {version}\n\nSample Rate: {sr}\n\nPitch Training: {pitch_guidance}\n\nHash (ID): {model_hash}\n\nCreation Time: {creation_date_str}\n\nVocoder: {vocoder}\n", "input_not_valid": "Please provide valid input!", "output_not_valid": "Please provide valid output!", "apply_effect": "apply effect", "enter_the_text": "Please enter the text to speech!", "choose_voice": "Please choose a voice!", "convert": "Converting {name}...", "separator_music": "music separation", "notfound": "Not found", "turn_on_use_audio": "Please enable using separated audio to proceed", "turn_off_convert_backup": "Disable backup voice conversion to use the original voice", "turn_off_merge_backup": "Disable merging backup voice to use the original voice", "not_found_original_vocal": "Original vocal not found!", "convert_vocal": "Converting voice...", "convert_success": "Voice conversion completed!", "convert_backup": "Converting backup voice...", "convert_backup_success": "Backup voice conversion completed!", "merge_backup": "Merging main voice with backup voice...", "merge_success": "Merge completed.", "is_folder": "Input is a folder: Converting all audio files in the folder...", "not_found_in_folder": "No audio files found in the folder!", "batch_convert": "Batch conversion in progress...", "batch_convert_success": "Batch conversion successful!", "create": "create", "provide_name": "Please provide a model name.", "not_found_data": "Data not found", "not_found_data_preprocess": "Processed audio data not found, please reprocess.", "not_found_data_extract": "Extracted audio data not found, please re-extract.", "provide_pretrained": "Please provide pre-trained {dg}.", "download_pretrained": "Download pre-trained {dg}{rvc_version} original", "not_found_pretrain": "Pre-trained {dg} not found", "not_use_pretrain": "No pre-trained model will be used", "training": "training", "display_title": "

🎵 Voice conversion and training interface created by Anh 🎵

", "rick_roll": "Click here if you want to be Rick Roll :) ---> [RickRoll]({rickroll})", "terms_of_use": "**Please do not use the project for any unethical, illegal, or harmful purposes to individuals or organizations...**", "exemption": "**In cases where users do not comply with the terms or violate them, I will not be responsible for any claims, damages, or liabilities, whether in contract, negligence, or other causes arising from, outside of, or related to the software, its use, or other transactions associated with it.**", "separator_tab": "Music Separation", "4_part": "A simple music separation system can separate into 4 parts: Instruments, Vocals, Main vocals, Backup vocals", "clear_audio": "Clean audio", "separator_backing": "Separate backup vocals", "denoise_mdx": "Denoise MDX separation", "use_mdx": "Use MDX", "dereveb_audio": "Remove vocal reverb", "dereveb_backing": "Remove backup reverb", "separator_model": "Music separation model", "separator_backing_model": "Backup separation model", "shift": "Shift", "shift_info": "Higher is better quality but slower and uses more resources", "segments_size": "Segments Size", "segments_size_info": "Higher is better quality but uses more resources", "batch_size": "Batch size", "batch_size_info": "Number of samples processed simultaneously in one training cycle. Higher can cause memory overflow", "mdx_batch_size_info": "Number of samples processed at a time. Batch processing optimizes calculations. Large batches can cause memory overflow; small batches reduce resource efficiency", "overlap": "Overlap", "overlap_info": "Overlap amount between prediction windows", "export_format": "Export format", "export_info": "The export format to export the audio file in", "output_separator": "Separated output", "hop_length_info": "Analyzing the time transfer window when performing transformations is allowed. The detailed value is compact but requires more calculation", "drop_audio": "Drop audio here", "drop_text": "Drop text file here", "use_url": "YouTube link", "url_audio": "Link audio", "downloads": "Downloads", "clean_strength": "Audio cleaning strength", "clean_strength_info": "Strength of the audio cleaner for filtering vocals during export", "input_output": "Audio input, output", "audio_path": "Input audio path", "refesh": "Refresh", "output_folder": "Output audio folder path", "output_folder_info": "Enter the folder path where the audio will be exported", "input_audio": "Audio input", "instruments": "Instruments", "original_vocal": "Original vocal", "main_vocal": "Main vocal", "backing_vocal": "Backup vocal", "convert_audio": "Convert Audio", "convert_info": "Convert audio using a trained voice model", "autotune": "Auto-tune", "use_audio": "Use separated audio", "convert_original": "Convert original voice", "convert_backing": "Convert backup voice", "not_merge_backing": "Do not merge backup voice", "merge_instruments": "Merge instruments", "pitch": "Pitch", "pitch_info": "Recommendation: set to 12 to change male voice to female and vice versa", "model_accordion": "Model and index", "model_name": "Model file", "index_path": "Index file", "index_strength": "Index strength", "index_strength_info": "Higher values increase strength. However, lower values may reduce artificial effects in the audio", "output_path": "Audio output path", "output_path_info": "Enter the output path (leave it as .wav format; it will auto-correct during conversion)", "setting": "General settings", "f0_method": "Extraction method", "f0_method_info": "Method used for data extraction", "f0_method_hybrid": "HYBRID extraction method", "f0_method_hybrid_info": "Combination of two or more different types of extracts", "hubert_model": "Embedding model", "hubert_info": "Pre-trained model to assist embedding", "modelname": "Model name", "modelname_info": "If you have your own model, just upload it and input the name here", "split_audio": "Split audio", "autotune_rate": "Auto-tune rate", "autotune_rate_info": "Level of auto-tuning adjustment", "resample": "Resample", "resample_info": "Resample post-processing to the final sample rate; 0 means no resampling, NOTE: SOME FORMATS DO NOT SUPPORT SPEEDS OVER 48000", "filter_radius": "Filter radius", "filter_radius_info": "If greater than three, median filtering is applied. The value represents the filter radius and can reduce breathiness or noise.", "volume_envelope": "Volume envelope", "volume_envelope_info": "Use the input volume envelope to replace or mix with the output volume envelope. The closer to 1, the more the output envelope is used", "protect": "Consonant protection", "protect_info": "Protect distinct consonants and breathing sounds to prevent audio tearing and other artifacts. Increasing this value provides comprehensive protection. Reducing it may reduce protection but also minimize indexing effects", "output_convert": "Converted audio", "main_convert": "Convert main voice", "main_or_backing": "Main voice + Backup voice", "voice_or_instruments": "Voice + Instruments", "convert_text": "Convert Text", "convert_text_markdown": "## Convert Text to Speech", "convert_text_markdown_2": "Convert text to speech and read aloud using the trained voice model", "input_txt": "Input data from a text file (.txt)", "text_to_speech": "Text to read", "voice_speed": "Reading speed", "voice_speed_info": "Speed of the voice", "tts_1": "1. Convert Text to Speech", "tts_2": "2. Convert Speech", "voice": "Voices by country", "output_tts": "Output speech path", "output_tts_convert": "Converted speech output path", "tts_output": "Enter the output path", "output_tts_markdown": "Unconverted and converted audio", "output_text_to_speech": "Generated speech from text-to-speech conversion", "output_file_tts_convert": "Speech converted using the model", "output_audio": "Audio output", "provide_output": "Enter the output path", "audio_effects": "Audio Effects", "apply_audio_effects": "## Add Additional Audio Effects", "audio_effects_edit": "Add effects to audio", "reverb": "Reverb effect", "chorus": "Chorus effect", "delay": "Delay effect", "more_option": "Additional options", "phaser": "Phaser effect", "compressor": "Compressor effect", "apply": "Apply", "reverb_freeze": "Freeze mode", "reverb_freeze_info": "Create a continuous echo effect when this mode is enabled", "room_size": "Room size", "room_size_info": "Adjust the room space to create reverberation", "damping": "Damping", "damping_info": "Adjust the level of absorption to control the amount of reverberation", "wet_level": "Reverb signal level", "wet_level_info": "Adjust the level of the reverb signal effect", "dry_level": "Original signal level", "dry_level_info": "Adjust the level of the signal without effects", "width": "Audio width", "width_info": "Adjust the width of the audio space", "chorus_depth": "Chorus depth", "chorus_depth_info": "Adjust the intensity of the chorus to create a wider sound", "chorus_rate_hz": "Frequency", "chorus_rate_hz_info": "Adjust the oscillation speed of the chorus effect", "chorus_mix": "Mix signals", "chorus_mix_info": "Adjust the mix level between the original and the processed signal", "chorus_centre_delay_ms": "Center delay (ms)", "chorus_centre_delay_ms_info": "The delay time between stereo channels to create the chorus effect", "chorus_feedback": "Feedback", "chorus_feedback_info": "Adjust the amount of the effect signal fed back into the original signal", "delay_seconds": "Delay time", "delay_seconds_info": "Adjust the delay time between the original and the processed signal", "delay_feedback": "Delay feedback", "delay_feedback_info": "Adjust the amount of feedback signal, creating a repeating effect", "delay_mix": "Delay signal mix", "delay_mix_info": "Adjust the mix level between the original and delayed signal", "fade": "Fade effect", "bass_or_treble": "Bass and treble", "limiter": "Threshold limiter", "distortion": "Distortion effect", "gain": "Audio gain", "bitcrush": "Bit reduction effect", "clipping": "Clipping effect", "fade_in": "Fade-in effect (ms)", "fade_in_info": "Time for the audio to gradually increase from 0 to normal level", "fade_out": "Fade-out effect (ms)", "fade_out_info": "the time it takes for the sound to fade from normal to zero", "bass_boost": "Bass boost level (dB)", "bass_boost_info": "amount of bass boost in audio track", "bass_frequency": "Low-pass filter cutoff frequency (Hz)", "bass_frequency_info": "frequencies are reduced. Low frequencies make the bass clearer", "treble_boost": "Treble boost level (dB)", "treble_boost_info": "high level of sound reinforcement in the audio track", "treble_frequency": "High-pass filter cutoff frequency (Hz)", "treble_frequency_info": "The frequency will be filtered out. The higher the frequency, the higher the sound will be retained.", "limiter_threashold_db": "Limiter threshold", "limiter_threashold_db_info": "Limit the maximum audio level to prevent it from exceeding the threshold", "limiter_release_ms": "Release time", "limiter_release_ms_info": "Time for the audio to return after being limited (Mili Seconds)", "distortion_info": "Adjust the level of distortion to create a noisy effect", "gain_info": "Adjust the volume level of the signal", "clipping_threashold_db": "Clipping threshold", "clipping_threashold_db_info": "Trim signals exceeding the threshold, creating a distorted sound", "bitcrush_bit_depth": "Bit depth", "bitcrush_bit_depth_info": "Reduce audio quality by decreasing bit depth, creating a distorted effect", "phaser_depth": "Phaser depth", "phaser_depth_info": "Adjust the depth of the effect, impacting its intensity", "phaser_rate_hz": "Frequency", "phaser_rate_hz_info": "Adjust the frequency of the phaser effect", "phaser_mix": "Mix signal", "phaser_mix_info": "Adjust the mix level between the original and processed signals", "phaser_centre_frequency_hz": "Center frequency", "phaser_centre_frequency_hz_info": "The center frequency of the phaser effect, affecting the adjusted frequencies", "phaser_feedback": "Feedback", "phaser_feedback_info": "Adjust the feedback level of the effect, creating a stronger or lighter phaser feel", "compressor_threashold_db": "Compressor threshold", "compressor_threashold_db_info": "The threshold level above which the audio will be compressed", "compressor_ratio": "Compression ratio", "compressor_ratio_info": "Adjust the level of audio compression when exceeding the threshold", "compressor_attack_ms": "Attack time (ms)", "compressor_attack_ms_info": "Time for compression to start taking effect after the audio exceeds the threshold", "compressor_release_ms": "Release time", "compressor_release_ms_info": "Time for the audio to return to normal after being compressed", "create_dataset_url": "Link to audio (use commas for multiple links)", "createdataset": "Create dataset", "create_dataset_markdown": "## Create Dataset training from YouTube", "create_dataset_markdown_2": "Process and create training datasets using YouTube links", "denoise": "Denoise", "skip": "Skip", "model_ver": "Voice separation version", "model_ver_info": "The model version for separating vocals", "create_dataset_info": "Dataset creation information", "output_data": "Dataset output", "output_data_info": "Output data after creation", "skip_start": "Skip beginning", "skip_start_info": "Skip the initial seconds of the audio; use commas for multiple audios", "skip_end": "Skip end", "skip_end_info": "Skip the final seconds of the audio; use commas for multiple audios", "training_model": "Train Model", "training_markdown": "Train and build a voice model with a set of voice data", "training_model_name": "Name of the model during training (avoid special characters or spaces)", "sample_rate": "Sample rate", "sample_rate_info": "Sample rate of the model", "training_version": "Model version", "training_version_info": "Version of the model during training", "training_pitch": "Pitch Guidance", "upload_dataset": "Upload dataset", "preprocess_effect": "Post processing", "clear_dataset": "Clean dataset", "preprocess_info": "Preprocessing information", "preprocess_button": "1. Processing", "extract_button": "2. Extract", "extract_info": "Data extraction information", "total_epoch": "Total epochs", "total_epoch_info": "Total training epochs", "save_epoch": "Save frequency", "save_epoch_info": "Frequency of saving the model during training to allow retraining", "create_index": "Create index", "index_algorithm": "Index algorithm", "index_algorithm_info": "Algorithm for creating the index", "custom_dataset": "Custom dataset folder", "custom_dataset_info": "Custom dataset folder for training data", "overtraining_detector": "Overtraining detector", "overtraining_detector_info": "Check for overtraining during model training", "cleanup_training": "Clean Up", "cleanup_training_info": "Only enable if you need to retrain the model from scratch.", "cache_in_gpu": "Cache in GPU", "cache_in_gpu_info": "Store the model in GPU cache memory", "dataset_folder": "Folder containing dataset", "threshold": "Overtraining threshold", "setting_cpu_gpu": "CPU/GPU settings", "gpu_number": "Number of GPUs used", "gpu_number_info": "Number of GPUs used during training", "save_only_latest": "Save only the latest", "save_only_latest_info": "Save only the latest D and G models", "save_every_weights": "Save all models", "save_every_weights_info": "Save all models after each epoch", "gpu_info": "GPU information", "gpu_info_2": "Information about the GPU used during training", "cpu_core": "Number of CPU cores available", "cpu_core_info": "Number of CPU cores used during training", "not_use_pretrain_2": "Do not use pretraining", "not_use_pretrain_info": "Do not use pre-trained models", "custom_pretrain": "Custom pretraining", "custom_pretrain_info": "Customize pre-training settings", "pretrain_file": "Pre-trained model file {dg}", "train_info": "Training information", "export_model": "5. Export Model", "zip_model": "2. Compress model", "output_zip": "Output file after compression", "model_path": "Model path", "model_ratio": "Model ratio", "model_ratio_info": "Adjusting towards one side will make the model more like that side", "output_model_path": "Model output path", "fushion": "Model Fusion", "fushion_markdown": "## Fushion Two Models", "fushion_markdown_2": "Combine two voice models into a single model", "read_model": "Read Information", "read_model_markdown": "## Read Model Information", "read_model_markdown_2": "Retrieve recorded information within the model", "drop_model": "Drop model here", "readmodel": "Read model", "model_path_info": "Enter the path to the model file", "modelinfo": "Model Information", "download_markdown": "## Download Model", "download_markdown_2": "Download voice models, pre-trained models, and embedding models", "model_download": "Download voice model", "model_url": "Link to the model", "15s": "Please wait about 15 seconds. The system will restart automatically!", "model_download_select": "Choose a model download method", "model_warehouse": "Model repository", "get_model": "Retrieve model", "name_to_search": "Name to search", "search_2": "Search", "select_download_model": "Choose a searched model (Click to select)", "download_pretrained_2": "Download pre-trained model", "only_huggingface": "Supports only huggingface.co", "pretrained_url": "Pre-trained model link {dg}", "select_pretrain": "Choose pre-trained model", "select_pretrain_info": "Choose a pre-trained model to download", "pretrain_sr": "Model sample rate", "drop_pretrain": "Drop pre-trained model {dg} here", "hubert_download": "Download embedding model", "hubert_url": "Link to embedding model", "drop_hubert": "Drop embedding model here", "settings": "Settings", "settings_markdown": "## Additional Settings", "settings_markdown_2": "Customize additional features of the project", "lang": "Language", "lang_restart": "The display language in the project (When changing the language, the system will automatically restart after 15 seconds to update)", "change_lang": "Change Language", "theme": "Theme", "theme_restart": "Theme type displayed in the interface (When changing the theme, the system will automatically restart after 15 seconds to update)", "theme_button": "Change Theme", "change_light_dark": "Switch Light/Dark Mode", "tensorboard_url": "Tensorboard URL", "errors_loading_audio": "Error loading audio: {e}", "apply_error": "An error occurred while applying effects: {e}", "indexpath": "Index path", "split_total": "Total parts split", "process_audio_error": "An error occurred while processing the audio", "merge_error": "An error occurred while merging audio", "not_found_convert_file": "Processed file not found", "convert_batch": "Batch conversion...", "found_audio": "Found {audio_files} audio files for conversion.", "not_found_audio": "No audio files found!", "error_convert": "An error occurred during audio conversion: {e}", "error_convert_batch": "An error occurred during the conversion of audio segments: {e}", "error_convert_batch_2": "An error occurred during batch audio conversion: {e}", "convert_batch_success": "Batch conversion completed successfully in {elapsed_time} seconds. {output_path}", "convert_audio_success": "File {input_path} converted successfully in {elapsed_time} seconds. {output_path}", "hybrid_methods": "Estimating f0 pitch using methods {methods}", "method_not_valid": "Invalid method", "read_faiss_index_error": "An error occurred while reading the FAISS index: {e}", "read_model_error": "Failed to load model: {e}", "starting_download": "Starting download", "version_not_valid": "Invalid vocal separation version", "skipaudio": "Cannot skip as skip time is greater than audio file length", "=<0": "Skip time is less than or equal to 0 and has been skipped", "skip_warning": "Skip duration ({seconds} seconds) exceeds audio length ({total_duration} seconds). Skipping.", "download_success": "Download completed successfully", "create_dataset_error": "An error occurred while creating the training dataset", "create_dataset_success": "Training dataset creation completed in {elapsed_time} seconds", "skip_start_audio": "Successfully skipped start of audio: {input_file}", "skip_end_audio": "Successfully skipped end of audio: {input_file}", "merge_audio": "Merged all parts containing audio", "separator_process": "Separating vocals: {input}...", "not_found_main_vocal": "Main vocal not found!", "not_found_backing_vocal": "Backup vocal not found!", "not_found_instruments": "Instruments not found", "merge_instruments_process": "Merging vocals with instruments...", "dereverb": "Removing vocal reverb", "dereverb_success": "Successfully removed vocal reverb", "save_index": "Index file saved", "create_index_error": "An error occurred while creating the index", "sr_not_16000": "Sample rate must be 16000", "gpu_not_valid": "Invalid GPU index. Switching to CPU.", "extract_file_error": "An error occurred while extracting the file", "extract_f0_method": "Starting pitch extraction using {num_processes} cores with method {f0_method}...", "extract_f0": "Pitch Extraction", "extract_f0_success": "Pitch extraction completed in {elapsed_time} seconds.", "NaN": "contains NaN values and will be ignored.", "start_extract_hubert": "Starting Embedding extraction...", "not_found_audio_file": "Audio file not found. Please ensure you provided the correct audio.", "process_error": "An error occurred during processing", "extract_hubert_success": "Embedding extraction completed in {elapsed_time} seconds.", "export_process": "Model path", "extract_error": "An error occurred during data extraction", "extract_success": "Data extraction successful", "min_length>=min_interval>=hop_size": "min_length must be greater than or equal to min_interval and hop_size", "max_sil_kept>=hop_size": "max_sil_kept must be greater than or equal to hop_size", "start_preprocess": "Starting data preprocessing with {num_processes} cores...", "not_integer": "Voice ID folder must be an integer; instead got", "preprocess_success": "Preprocessing completed in {elapsed_time} seconds.", "preprocess_model_success": "Preprocessing data for the model completed successfully", "turn_on_dereverb": "Reverb removal for backup vocals requires enabling reverb removal", "turn_on_separator_backing": "Backup vocal separation requires enabling vocal separation", "backing_model_ver": "Backup vocal separation model version", "clean_audio_success": "Audio cleaned successfully!", "separator_error": "An error occurred during music separation", "separator_success": "Music separation completed in {elapsed_time} seconds", "separator_process_2": "Processing music separation", "separator_success_2": "Music separation successful!", "separator_process_backing": "Processing backup vocal separation", "separator_process_backing_success": "Backup vocal separation successful!", "process_original": "Processing original vocal reverb removal...", "process_original_success": "Original vocal reverb removal successful!", "process_main": "Processing main vocal reverb removal...", "process_main_success": "Main vocal reverb removal successful!", "process_backing": "Processing backup vocal reverb removal...", "process_backing_success": "Backup vocal reverb removal successful!", "save_every_epoch": "Save model after: ", "total_e": "Total epochs: ", "dorg": "Pre-trained G: {pretrainG} | Pre-trained D: {pretrainD}", "training_f0": "Pitch Guidance", "not_gpu": "No GPU detected, reverting to CPU (not recommended)", "not_found_checkpoint": "Checkpoint file not found: {checkpoint_path}", "save_checkpoint": "Reloaded checkpoint '{checkpoint_path}' (epoch {checkpoint_dict})", "save_model": "Saved model '{checkpoint_path}' (epoch {iteration})", "sr_does_not_match": "{sample_rate} Sample rate does not match target {sample_rate2} Sample rate", "spec_error": "An error occurred while retrieving specifications from {spec_filename}: {e}", "time_or_speed_training": "time={current_time} | training speed={elapsed_time_str}", "savemodel": "Saved model '{model_dir}' (epoch {epoch} and step {step})", "model_author": "Credit model to {model_author}", "unregistered": "Model unregistered", "not_author": "Model not credited", "training_author": "Model creator name", "training_author_info": "To credit the model, enter your name here", "extract_model_error": "An error occurred while extracting the model", "start_training": "Starting training", "import_pretrain": "Loaded pre-trained model ({dg}) '{pretrain}'", "not_using_pretrain": "No pre-trained model ({dg}) will be used", "training_warning": "WARNING: Generated loss is lower than the lower threshold loss for the next epoch.", "overtraining_find": "Overtraining detected at epoch {epoch} with smoothed generator loss {smoothed_value_gen} and smoothed discriminator loss {smoothed_value_disc}", "best_epoch": "New best epoch {epoch} with smoothed generator loss {smoothed_value_gen} and smoothed discriminator loss {smoothed_value_disc}", "success_training": "Training completed with {epoch} epochs, {global_step} steps, and {loss_gen_all} total generator loss.", "training_info": "Lowest generator loss: {lowest_value_rounded} at epoch {lowest_value_epoch}, step {lowest_value_step}", "model_training_info": "{model_name} | epoch={epoch} | step={global_step} | {epoch_recorder} | lowest value={lowest_value_rounded} (epoch {lowest_value_epoch} and step {lowest_value_step}) | remaining epochs for overtraining: g/total: {remaining_epochs_gen} d/total: {remaining_epochs_disc} | smoothed generator loss={smoothed_value_gen} | smoothed discriminator loss={smoothed_value_disc}", "model_training_info_2": "{model_name} | epoch={epoch} | step={global_step} | {epoch_recorder} | lowest value={lowest_value_rounded} (epoch {lowest_value_epoch} and step {lowest_value_step})", "model_training_info_3": "{model_name} | epoch={epoch} | step={global_step} | {epoch_recorder}", "training_error": "An error occurred while training the model:", "separator_info": "Initializing with output path: {output_dir}, output format: {output_format}", "output_dir_is_none": "Output folder not specified. Using current working directory.", ">0or=1": "Normalization threshold must be greater than 0 and less than or equal to 1.", "output_single": "Single root output requested; only one file ({output_single_stem}) will be written", "step2": "The second step will be reversed using spectrogram instead of waveform. This may improve quality but is slightly slower.", "name_ver": "Version {name}", "os": "Operating System", "platform_info": "System: {system_info} Name: {node} Release: {release} Machine: {machine} Processor: {processor}", "none_ffmpeg": "FFmpeg is not installed. Please install FFmpeg to use this package.", "install_onnx": "ONNX Runtime package {pu} installed with version", "running_in_cpu": "Unable to configure hardware acceleration, running in CPU mode", "running_in_cuda": "CUDA available in Torch, setting Torch device to CUDA", "onnx_have": "ONNXruntime available {have}, enabling acceleration", "onnx_not_have": "{have} not available in ONNXruntime; acceleration will NOT be enabled", "python_not_install": "Python package: {package_name} is not installed", "hash": "Calculating hash for model file {model_path}", "ioerror": "IOError while seeking -10 MB or reading model file to compute hash: {e}", "cancel_download": "File already exists at {output_path}, skipping download", "download_model": "Downloading file from {url} to {output_path} with a timeout of 300 seconds", "download_error": "Failed to download file from {url}, response code: {status_code}", "vip_model": "Model: '{model_friendly_name}' is a premium model intended by Anjok07 only for paid subscriber access.", "vip_print": "Hey there, if you haven't subscribed, please consider supporting UVR's developer, Anjok07, by subscribing here: https://patreon.com/uvr", "search_model": "Searching for model {model_filename} in the list of supported models in the group", "load_download_json": "Downloaded model list loaded", "single_model": "Identified single model file: {model_friendly_name}", "not_found_model": "Model not found in the UVR repository, attempting to download from the audio model separation repository...", "single_model_path": "Returning path for single model file: {model_path}", "find_model": "Input file name {model_filename} found in multi-file model: {model_friendly_name}", "find_models": "Identified multi-file model: {model_friendly_name}, iterating through files to download", "find_path": "Attempting to determine download PATH for config pair", "not_found_model_warehouse": "Model not found in the UVR repository, attempting to download from the audio model separation repository...", "yaml_warning": "The model name you specified, {model_filename}, is actually a model config file rather than a model file.", "yaml_warning_2": "We found a model matching this config file: {config_key}, so we'll use that model file for this run.", "yaml_warning_3": "To avoid confusing/inconsistent behavior in the future, specify the actual model file name instead.", "yaml_debug": "Config YAML model file not found in UVR repository, attempting to download from the audio model separation repository...", "download_model_friendly": "All files downloaded for model {model_friendly_name}, returning original path {model_path}", "not_found_model_2": "Model file {model_filename} not found in the supported files", "load_yaml": "Loading model data from YAML at path {model_data_yaml_filepath}", "load_yaml_2": "Model data loaded from YAML file: {model_data}", "hash_md5": "Computing MD5 hash for model file to identify model parameters from UVR data...", "model_hash": "Model {model_path} has hash {model_hash}", "mdx_data": "MDX model data path set to {mdx_model_data_path}", "load_mdx": "Loading MDX model parameters from UVR model data file...", "model_not_support": "Unsupported model file: no parameters found for MD5 hash {model_hash} in UVR model data for MDX vault.", "uvr_json": "Model data loaded from UVR JSON with hash {model_hash}: {model_data}", "loading_model": "Loading model {model_filename}...", "download_model_friendly_2": "Downloaded model, friendly name: {model_friendly_name}, Model path: {model_path}", "model_type_not_support": "Unsupported model type: {model_type}", "demucs_not_support_python<3.10": "Demucs models require Python version 3.10 or higher.", "import_module": "Importing module for model type", "initialization": "Initializing separator class for model type", "loading_model_success": "Model loading completed.", "loading_model_duration": "Model loading duration", "starting_separator": "Starting separation process for audio file path", "normalization": "Normalization threshold set to {normalization_threshold}, waveform will be scaled down to this maximum amplitude to prevent clipping.", "loading_separator_model": "Downloading model {model_filename}...", "separator_success_3": "Separation process completed.", "separator_duration": "Separation duration", "downloading_model": "Downloaded model, type: {model_type}, friendly name: {model_friendly_name}, Model path: {model_path}, Model data: {model_data_dict_size} items", "demucs_info": "Demucs parameters: Segment size = {segment_size}, Segment size active = {segments_enabled}", "demucs_info_2": "Demucs parameters: Number of predictions = {shifts}, Overlap = {overlap}", "start_demucs": "Demucs Separator initialization completed", "start_separator": "Starting separation process...", "prepare_mix": "Preparing mixture...", "demix": "Mixture prepared for demixing. Shape: {shape}", "cancel_mix": "Loading model for demixing...", "model_review": "Model loaded and set to evaluation mode.", "del_gpu_cache_after_demix": "Cleared model and GPU cache after demixing.", "process_output_file": "Processing output file...", "source_length": "Processing source array, source length is {source_length}", "process_ver": "Processing source version...", "set_map": "Set source map to {part} parts...", "process_all_part": "Processing for all root parts...", "skip_part": "Skipping root part {stem_name} as out_single_stem is set to {output_single_stem}...", "starting_demix_demucs": "Starting the demix process in demix_demucs...", "model_infer": "Running model inference...", "name_not_pretrained": "{name} is not a pre-trained model or a model bundle.", "invalid_checksum": "Invalid checksum for file {path}, expected {checksum} but got {actual_checksum}", "mdx_info": "MDX parameters: Batch size = {batch_size}, Segment size = {segment_size}", "mdx_info_2": "MDX parameters: Overlap = {overlap}, Hop_length = {hop_length}, Denoising enabled = {enable_denoise}", "mdx_info_3": "MDX parameters", "load_model_onnx": "Loading ONNX model for inference...", "load_model_onnx_success": "Successfully loaded model using ONNXruntime inference session.", "onnx_to_pytorch": "Model converted from ONNX to PyTorch due to mismatched segment size with dim_t, processing may be slower.", "stft": "Inverse STFT applied. Returning result with shape", "no_denoise": "Model running on spectrum without denoising.", "mix": "Preparing mix for input audio file {audio_file_path}...", "normalization_demix": "Normalizing mix prior to demixing...", "mix_success": "Mix preparation completed.", "primary_source": "Normalizing primary source...", "secondary_source": "Producing secondary source: Mixing in compatible mode", "invert_using_spec": "Inverting secondary stem using spectrum when invert_USE_spec is set to True", "invert_using_spec_2": "Inverting secondary stem by subtracting transformed stem from the initial transformed mix", "enable_denoise": "Model running on both positive and negative spectrums for denoising.", "is_match_mix": "is_match_mix: Predicted spectrum obtained directly from STFT output.", "save_secondary_stem_output_path": "Saving secondary stem {stem_name} to {stem_output_path}...", "starting_model": "Initializing model settings...", "input_info": "Model input parameters", "model_settings": "Model settings", "initialize_mix": "Initializing mix with is_ckpt = {is_ckpt}. Initial mix shape: {shape}", "!=2": "Expected 2-channel audio signal but got {shape} channels", "process_check": "Processing in checkpoint mode...", "stft_2": "STFT applied to mix. Spectrum shape: {shape}", "cache": "Computed padding", "shape": "Mix shape after padding: {shape}, Number of parts: {num_chunks}", "process_no_check": "Processing in no-checkpoint mode...", "n_sample_or_pad": "Number of samples: {n_sample}, Computed padding: {pad}", "shape_2": "Mix shape after padding", "process_part": "Processed part {mix_waves}: Start {i}, End {ii}", "mix_waves_to_tensor": "Converted mix_waves to tensor. Tensor shape: {shape}", "mix_match": "Mix mode Match; applying compensation factor.", "tar_waves": "tar_waves. Shape", "normalization_2": "Normalizing result by dividing it by divisor.", "mix_wave": "Processing mix_wave batch", "mix_or_batch": "Mix parts into batches. Number of batches", "demix_is_match_mix": "Starting demix process with is_match_mix,", "mix_shape": "Root mix parts stored. Shape", "chunk_size_or_overlap": "Chunk size for compatible mixing: {chunk_size}, Overlap: {overlap}", "chunk_size_or_overlap_standard": "Standard chunk size: {chunk_size}, Overlap: {overlap}", "calc_size": "Generated size calculated", "window": "Window applied to this segment.", "process_part_2": "Processing segment {total}/{total_chunks}: Start {start}, End {end}", "all_process_part": "Total segments to process", "step_or_overlap": "Step size to process parts: {step} with overlap set to {overlap}.", "mix_cache": "Mix prepared with padding. Mix shape", "dims": "Cannot use sin/cos position encoding with odd dimensions (dim={dims})", "activation": "activation must be relu/gelu, not {activation}", "length_or_training_length": "Provided length {length} exceeds training duration {training_length}", "type_not_valid": "Invalid type for", "del_parameter": "Removing non-existent parameter ", "info": "Common parameters: Model name = {model_name}, Model path = {model_path}", "info_2": "Common parameters: Output path = {output_dir}, Output format = {output_format}", "info_3": "Common parameters: Normalization threshold = {normalization_threshold}", "info_4": "Common parameters: Denoising enabled = {enable_denoise}, Single stem output = {output_single_stem}", "info_5": "Common parameters: Inversion using specs = {invert_using_spec}, Sample rate = {sample_rate}", "info_6": "Common parameters: Primary root name = {primary_stem_name}, Secondary root name = {secondary_stem_name}", "info_7": "Common parameters: Karaoke mode = {is_karaoke}, BV model = {is_bv_model}, BV model rebalancing = {bv_model_rebalance}", "success_process": "Completed processing root {stem_name} and writing audio...", "load_audio": "Loading audio from file", "load_audio_success": "Audio loaded. Sample rate: {sr}, Audio shape: {shape}", "convert_mix": "Converting provided mix array.", "convert_shape": "Converted mix shape: {shape}", "audio_not_valid": "Audio file {audio_path} is empty or invalid", "audio_valid": "Audio file is valid and contains data.", "mix_single": "Mix is mono. Converting to stereo.", "convert_mix_audio": "Converted to stereo mix.", "mix_success_2": "Mix preparation completed.", "duration": "Audio duration is {duration_hours} hours ({duration_seconds} seconds).", "write": "Using {name} to write.", "write_audio": "Writing {name} with root path:", "original_not_valid": "Warning: Original source array is nearly silent or empty.", "shape_audio": "Audio data shape before processing", "convert_data": "Data type before conversion", "original_source_to_int16": "Converted original_source to int16.", "shape_audio_2": "Interleaved audio data shape", "create_audiosegment": "Successfully created AudioSegment.", "create_audiosegment_error": "Specific error while creating AudioSegment", "export_error": "Error exporting audio file", "export_success": "Successfully exported audio file to", "clean": "Running garbage collection...", "clean_cache": "Clearing {name} cache...", "del_path": "Deleting path, source, and root of input audio file...", "not_success": "Process was not successful: ", "resample_error": "Error during resampling", "shapes": "Shapes", "wav_resolution": "Resolution type", "warnings": "Warning: Extremely aggressive values detected", "warnings_2": "Warning: NaN or infinite values detected in wave input. Shape", "process_file": "Processing file... \n", "save_instruments": "Saving reverse track...", "assert": "Audio files must have the same shape - Mix: {mixshape}, Inst: {instrumentalshape}", "rubberband": "Rubberband CLI cannot be executed. Please ensure Rubberband-CLI is installed.", "rate": "Rate must be strictly positive", "gdown_error": "Could not retrieve the public link for the file. You may need to change its permissions to 'Anyone with the link' or there may already be excessive access permissions.", "to": "To:", "gdown_value_error": "A path or ID must be specified", "missing_url": "URL is missing", "mac_not_match": "MAC does not match", "file_not_access": "File is not accessible", "int_resp==-3": "Request failed, retrying", "search_separate": "Search for separate files...", "found_choice": "Found {choice}", "separator==0": "No separate files found!", "select_separate": "Select separate files", "start_app": "Starting interface...", "provide_audio": "Enter the path to the audio file", "set_torch_mps": "Set Torch device to MPS", "googletts": "Convert text using Google", "pitch_info_2": "Pitch adjustment for text-to-speech converter", "waveform": "Waveform must have the shape (# frames, # channels)", "freq_mask_smooth_hz": "freq_mask_smooth_hz must be at least {hz}Hz", "time_mask_smooth_ms": "time_mask_smooth_ms must be at least {ms}ms", "x": "x must be greater", "xn": "xn must be greater", "not_found_pid": "No processes found!", "end_pid": "Process terminated!", "clean_audios": "Starting audio cleanup...", "clean_audios_success": "Audio file cleanup complete!", "clean_separate": "Starting cleanup of separation model...", "clean_separate_success": "Separation model cleanup complete!", "clean_model": "Starting model cleanup...", "clean_model_success": "Model file cleanup complete!", "clean_index": "Starting index cleanup...", "clean_index_success": "Index file cleanup complete!", "clean_pretrain": "Starting pretrained model cleanup...", "clean_pretrain_success": "Pretrained model cleanup complete!", "clean_all_audios": "Starting cleanup of all audio files...", "clean_all_audios_success": "All audio file cleanup complete!", "not_found_separate_model": "No separation model files found!", "clean_all_separate_model": "Starting cleanup of all separation model files...", "clean_all_separate_model_success": "All separation model files cleanup complete!", "clean_all_models_success": "All model files cleanup complete", "not_found_pretrained": "No pretrained model files found!", "clean_all_pretrained": "Starting cleanup of all pretrained model files...", "clean_all_pretrained_success": "All pretrained model cleanup complete!", "not_found_log": "No log files found!", "clean_all_log": "Starting cleanup of all log files...", "clean_all_log_success": "Log file cleanup complete!", "not_found_predictors": "No predictor model files found!", "clean_all_predictors": "Starting cleanup of all predictor model files...", "clean_all_predictors_success": "Predictor model cleanup complete!", "not_found_embedders": "No embedder model files found!", "clean_all_embedders": "Starting cleanup of all embedder model files...", "clean_all_embedders_success": "Embedder model cleanup complete!", "provide_folder": "Please provide a valid folder!", "empty_folder": "The data folder is empty!", "clean_dataset": "Starting dataset folder cleanup...", "clean_dataset_success": "Dataset folder cleanup complete!", "vocoder": "Vocoder", "vocoder_info": "A vocoder analyzes and synthesizes human speech signals for voice transformation.", "code_error": "Error: Received status code", "json_error": "Error: Unable to parse response.", "requests_error": "Request failed: {e}", "memory_efficient_training": "Using memory-efficient training", "not_use_pretrain_error_download": "Will not use pretrained models due to missing files", "start_clean_model": "Starting cleanup of all models...", "provide_file_settings": "Please provide a preset settings file!", "load_presets": "Loaded preset file {presets}", "provide_filename_settings": "Please provide a preset file name!", "choose1": "Please select one to export!", "export_settings": "Exported preset file {name}", "use_presets": "Using preset file", "file_preset": "Preset file", "load_file": "Load file", "export_file": "Export preset file", "save_clean": "Save cleanup", "save_autotune": "Save autotune", "save_pitch": "Save pitch", "save_index_2": "Save index impact", "save_resample": "Save resampling", "save_filter": "Save median filter", "save_envelope": "Save sound envelope", "save_protect": "Save sound protection", "save_split": "Save sound split", "filename_to_save": "File name to save", "upload_presets": "Upload preset file", "stop": "Stop process", "stop_separate": "Stop Music Separation", "stop_convert": "Stop Conversion", "stop_create_dataset": "Stop Dataset Creation", "stop_training": "Stop Training", "stop_extract": "Stop Data Processing", "stop_preprocess": "Stop Data Extraction", "cleaner": "Cleaner", "clean_audio": "Clean audio files", "clean_all": "Clean all", "clean_file": "Clean file", "clean_models": "Clean model files", "clean_pretrained": "Clean pretrained model files", "clean_separated": "Clean separated model files", "clean_presets": "Clean preset files", "clean_datasets": "Clean training dataset folder", "clean_dataset_folder": "Clean dataset folder", "clean_log": "Clean log files", "clean_predictors": "Clean predictor models", "clean_embed": "Clean embedder models", "clean_presets_2": "Starting cleanup of preset files...", "clean_presets_success": "Preset file cleanup complete!", "not_found_presets": "No preset files found in the folder!", "clean_all_presets": "Starting cleanup of all preset files...", "clean_all_presets_success": "All preset file cleanup complete!", "port": "Port {port} is unavailable! Lowering port by one...", "empty_json": "{file}: Corrupted or empty", "thank": "Thank you for reporting the issue, and apologies for any inconvenience caused!", "error_read_log": "An error occurred while reading log files!", "error_send": "An error occurred while sending the report! Please contact me on Discord: pham_huynh_anh!", "report_bugs": "Report Bugs", "agree_log": "Agree to provide all log files", "error_info": "Error description", "error_info_2": "Provide more information about the error", "report_bug_info": "Report bugs encountered during program usage", "sr_info": "NOTE: SOME FORMATS DO NOT SUPPORT RATES ABOVE 48000", "report_info": "If possible, agree to provide log files to help with debugging.\n\nIf log files are not provided, please describe the error in detail, including when and where it occurred.\n\nIf this reporting system also fails, you can reach out via [ISSUE]({github}) or Discord: `pham_huynh_anh`", "default_setting": "An error occurred during separation, resetting all settings to default...", "dataset_folder1": "Please enter the data folder name", "checkpointing_err": "Pretrained model parameters such as sample rate or architecture do not match the selected model.", "start_onnx_export": "Start converting model to onnx", "convert_model": "Convert Model", "pytorch2onnx": "Converting PYTORCH Model to ONNX Model", "pytorch2onnx_markdown": "Convert RVC model from pytorch to onnx to optimize audio conversion", "error_readfile": "An error occurred while reading the file!", "read_sf": "Read audio file using soundfile...", "read_librosa": "Read audio files using librosa as soundfile is not supported...", "f0_onnx_mode": "F0 ONNX Mode", "f0_onnx_mode_info": "Extracting pitch using the ONNX model can help improve speed", "formantshift": "Pitch and Formant Shift", "formant_qfrency": "Frequency for Formant Shift", "formant_timbre": "Timbre for Formant Transformation", "time_frames": "Time (Frames)", "Frequency": "Frequency (Hz)", "f0_extractor_tab": "F0 Extraction", "f0_extractor_markdown": "## Pitch Extraction", "f0_extractor_markdown_2": "F0 pitch extraction is intended for use in audio conversion inference", "start_extract": "Starting extraction process...", "extract_done": "Extraction process completed!", "f0_file": "Use pre-extracted F0 file", "upload_f0": "Upload F0 file", "f0_file_2": "F0 File", "clean_f0_file": "Clean up F0 file", "start_clean_f0": "Starting F0 file cleanup...", "clean_f0_done": "F0 file cleanup completed!", "embed_onnx": "Embedders ONNX Mode", "embed_onnx_info": "Embedded extraction using the ONNX model can help improve speed" }