| { | |
| "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}.", | |
| "unable_analyze_model": "Unable to analyze the model!", | |
| "download_pretrain": "Downloading pre-trained model...", | |
| "provide_pretrain": "Please provide a pre-trained model url {dg}.", | |
| "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\nEnergy: {rms_extract}\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", | |
| "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 separation", | |
| "use_mdx": "Use MDX", | |
| "dereveb_audio": "Remove vocal reverb", | |
| "dereveb_model": "Reverb separation model", | |
| "separator_model": "Music separation model", | |
| "separator_backing_model": "Backup separation model", | |
| "shift": "Shift", | |
| "shift_info": "Higher is better quality but 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": "The number of samples processed at once. Dividing into batches optimizes the calculation process", | |
| "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", | |
| "refresh": "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.", | |
| "rms_mix_rate": "RMS Mix Rate", | |
| "rms_mix_rate_info": "Determines the blend ratio between the RMS energy of the original voice and the converted voice", | |
| "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": "Speech speed", | |
| "voice_speed_info": "Speed of the voice", | |
| "tts_1": "1. Convert Text to Speech", | |
| "tts_2": "2. Convert Audio", | |
| "voice": "Voice by language", | |
| "output_tts": "Output TTS path", | |
| "output_tts_convert": "Converted TTS path", | |
| "tts_output": "Enter the output path", | |
| "output_tts_markdown": "Unconverted and converted audio", | |
| "output_text_to_speech": "TTS Output", | |
| "output_file_tts_convert": "Conversion Output", | |
| "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_threshold_db": "Limiter threshold", | |
| "limiter_threshold_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_threshold_db": "Clipping threshold", | |
| "clipping_threshold_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_threshold_db": "Compressor threshold", | |
| "compressor_threshold_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. Preprocessing Data", | |
| "extract_button": "2. Extracting Data", | |
| "extract_info": "Extraction information", | |
| "total_epoch": "Total epochs", | |
| "total_epoch_info": "Total training epochs", | |
| "save_epoch": "Save every epoch", | |
| "save_epoch_info": "Determine at how many epochs the model will saved at", | |
| "create_index": "Generate 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": "Clean up and retrain 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": "The order number of GPUs used in training. (Note: AMD GPUs do not support multi-GPU 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 model 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", | |
| "30s": "Please wait about 30 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", | |
| "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 samplerate", | |
| "drop_pretrain": "Drop pre-trained model {dg} 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 30 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 30 seconds to update)", | |
| "theme_button": "Change Theme", | |
| "change_light_dark": "Switch Light/Dark Mode", | |
| "tensorboard_url": "Tensorboard URL", | |
| "errors_loading_audio": "Error loading audio", | |
| "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}", | |
| "convert_batch_success": "Batch conversion completed successfully in {elapsed_time} seconds. Output {output_path}", | |
| "convert_audio_success": "File {input_path} converted successfully in {elapsed_time} seconds. Output {output_path}", | |
| "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", | |
| "skip<audio": "Cannot skip as skip time is less than audio file length", | |
| "skip>audio": "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", | |
| "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...", | |
| "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", | |
| "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", | |
| "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!", | |
| "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", | |
| "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", | |
| "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}", | |
| "none_ffmpeg": "FFmpeg is not installed. Please install FFmpeg to use this package.", | |
| "running_in_cpu": "Unable to configure hardware acceleration, running in CPU mode", | |
| "running_in_cuda": "CUDA available in Torch, setting Torch device to CUDA", | |
| "running_in_amd": "AMD available in Torch, setting Torch device to AMD", | |
| "onnx_have": "ONNXruntime available {have}, enabling acceleration", | |
| "onnx_not_have": "{have} not available in ONNXruntime; acceleration will NOT be enabled", | |
| "download_error": "Failed to download file from {url}, response code: {status_code}", | |
| "loading_model": "Loading model {model_filename}...", | |
| "model_type_not_support": "Unsupported model type: {model_type}", | |
| "starting_separator": "Starting separation process for audio file path", | |
| "separator_success_3": "Separation process completed.", | |
| "separator_duration": "Separation duration", | |
| "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 ", | |
| "convert_shape": "Converted mix shape: {shape}", | |
| "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.", | |
| "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", | |
| "not_found_pid": "No processes found!", | |
| "end_pid": "Process terminated!", | |
| "not_found_separate_model": "No separation model files found!", | |
| "not_found_pretrained": "No pretrained model files found!", | |
| "not_found_log": "No log files found!", | |
| "not_found_predictors": "No predictor model files found!", | |
| "not_found_embedders": "No embedder model files found!", | |
| "provide_folder": "Please provide a valid folder!", | |
| "empty_folder": "The data folder is empty!", | |
| "vocoder": "Vocoder", | |
| "vocoder_info": "A vocoder analyzes and synthesizes human speech signals for voice transformation.\n\nDefault: This option is HiFi-GAN-NSF, compatible with all RVCs\n\nMRF-HiFi-GAN: Higher fidelity.\n\nRefineGAN: Superior sound quality.", | |
| "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", | |
| "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_preprocess": "Stop Data Processing", | |
| "stop_extract": "Stop Data Extraction", | |
| "not_found_presets": "No preset files found in the folder!", | |
| "port": "Port {port} is unavailable! Lowering port by one...", | |
| "empty_json": "{file}: Corrupted or empty", | |
| "sr_info": "NOTE: SOME FORMATS DO NOT SUPPORT RATES ABOVE 48000", | |
| "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!", | |
| "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", | |
| "embed_mode": "Embedders Mode", | |
| "embed_mode_info": "Extracting embeddings using different models", | |
| "close": "The application is shutting down...", | |
| "start_whisper": "Starting voice recognition with Whisper...", | |
| "whisper_done": "Voice recognition complete!", | |
| "process_audio": "Preprocessing audio...", | |
| "process_done_start_convert": "Audio processing complete! proceeding with audio conversion...", | |
| "convert_with_whisper": "Convert Audio With Whisper", | |
| "convert_with_whisper_info": "Convert audio using a trained speech model with a Whisper model for speech recognition\n\nWhisper will recognize different voices then cut the individual voices and use the RVC model to convert those segments\n\nThe Whisper model may not work properly which may cause strange output", | |
| "num_spk": "Number of voices", | |
| "num_spk_info": "Number of voices in the audio", | |
| "model_size": "Whisper model size", | |
| "model_size_info": "Whisper model size\n\nLarge models can produce strange outputs", | |
| "title": "Simple high-quality and high-performance voice and instrument conversion and training tool for Vietnamese people", | |
| "fp16_not_support": "CPU, MPS and OCL does not support fp16 well, convert fp16 -> fp32", | |
| "precision": "Precision", | |
| "precision_info": "Precision of inference and model training\n\nNote: CPU, OPENCL Does not support fp16", | |
| "update_precision": "Update Precision", | |
| "start_update_precision": "Start updating precision", | |
| "deterministic": "Deterministic algorithm", | |
| "deterministic_info": "When enabled, highly deterministic algorithms are used, ensuring that each run of the same input data will yield the same results.\n\nWhen disabled, more optimal algorithms may be selected but may not be fully deterministic, resulting in different training results between runs.", | |
| "benchmark": "Benchmark algorithm", | |
| "benchmark_info": "When enabled, it will test and select the most optimized algorithm for the specific hardware and size. This can help speed up training.\n\nWhen disabled, it will not perform this algorithm optimization, which can reduce speed but ensures that each run uses the same algorithm, which is useful if you want to reproduce exactly.", | |
| "font": "Font", | |
| "font_info": "Interface font\n\nVisit [Google Font](https://fonts.google.com) to choose your favorite font.", | |
| "change_font": "Change Font", | |
| "f0_unlock": "Unlock all", | |
| "f0_unlock_info": "Unlock all pitch extraction methods", | |
| "srt": "SRT file is empty or corrupt!", | |
| "optimizer": "Optimizer", | |
| "optimizer_info": "Optimizer in training, AdamW is default.", | |
| "main_volume": "Main audio file volume", | |
| "main_volume_info": "Main audio file volume. Should be between -4 and 0.", | |
| "combination_volume": "Combination audio file volume", | |
| "combination_volume_info": "Combination audio file volume. Should keep the volume of the combination file lower than the main audio.", | |
| "inference": "Inference", | |
| "extra": "Extra", | |
| "running_local_url": "Running Interface On Local Url", | |
| "running_share_url": "Running Interface On Public Url", | |
| "translate": "Translate", | |
| "source_lang": "Input language", | |
| "target_lang": "Output language", | |
| "prompt_warning": "Please enter text to start translating!", | |
| "read_error": "An error occurred while reading the text file!", | |
| "quirk": "Quirk Effects", | |
| "quirk_info": "## Weird Effects for Audio", | |
| "quirk_label": "Quirk effects", | |
| "quirk_label_info": "Quirk effects that can be used to apply to audio", | |
| "quirk_markdown": "Apply quirky effects to your audio to make it weird and weird.", | |
| "gradio_start": "Interface loaded successfully after", | |
| "quirk_choice": {"Random": 0, "Voice Crack": 1, "Horror": 2, "Robot": 3, "Baby": 4, "Depression": 5, "Voice Jerking": 6, "Oldster": 7, "Echo": 8, "Devil": 9, "Distorted Voice": 10, "Online Sales": 11, "Drag": 12, "Uncomfortable": 13, "Noise": 14, "Connectivity Issue": 15, "Disorder": 16}, | |
| "proposal_pitch": "Automatically propose pitch", | |
| "hybrid_calc": "Hybrid calculation for method: {f0_method}...", | |
| "proposal_f0": "Proposed pitch: {up_key}", | |
| "startautotune": "Start autotune pitch...", | |
| "rms_start_extract": "Starting audio energy extraction with {num_processes} cores...", | |
| "rms_success_extract": "Energy extraction completed in {elapsed_time} seconds.", | |
| "train&energy": "Training with energy", | |
| "train&energy_info": "Training model with RMS energy", | |
| "editing": "Editing", | |
| "check_assets_error": "Downloading assets failed {count} times in a row! Please download manually and place in the assets folder: https://huggingface.co/AnhP/Vietnamese-RVC-Project", | |
| "csrt": "Start speech recognition to create srt file...", | |
| "start_rpc": "Start RPC rendering", | |
| "stop_rpc": "RPC rendering stopped", | |
| "details": "Simple high-performance and high-quality speech converter.", | |
| "use": "Using the interface...", | |
| "create_srt_tab": "Create SRT file", | |
| "create_srt_markdown": "## Create SRT File From Audio File", | |
| "create_srt_markdown_2": "Use Whisper to convert audio file to text and create srt file", | |
| "srt_content": "SRT file content", | |
| "word_timestamps": "Word Timestamps", | |
| "word_timestamps_info": "Provides the start and end time of each word in the audio file converted to text.", | |
| "srt_output_file": "Output SRT file", | |
| "proposal_pitch_threshold": "Proposal pitch threshold", | |
| "proposal_pitch_threshold_info": "Proposal pitch frequency threshold, for male models used at 155.0 and female models at 255.0", | |
| "hop_length": "Hop Length", | |
| "aggression": "Aggressiveness", | |
| "window_size": "Window size", | |
| "post_process_threshold": "Post-processing threshold", | |
| "enable_tta": "Enable TTA", | |
| "high_end_process": "High-end processing", | |
| "enable_post_process": "Post-processing", | |
| "window_size_info": "A smaller window size will yield higher quality output, but will take longer to process.", | |
| "aggression_info": "Main body extraction intensity.", | |
| "post_process_threshold_info": "The level of post-processing after the music is extracted.", | |
| "denoise_model": "Denoise model", | |
| "audio_processing": "Input/output processing", | |
| "create_pipeline_error": "An error occurred while creating the pipeline", | |
| "voice_changer_selected_error": "An error occurred while selecting voice changer", | |
| "latency": "Latency", | |
| "start_realtime": "Starting Realtime...", | |
| "provide_audio_device": "Please select valid input and output devices!", | |
| "provide_monitor_device": "Please select a valid monitor!", | |
| "realtime_is_ready": "Realtime is ready!", | |
| "realtime_has_stop": "Realtime has stopped!", | |
| "stop_realtime": "Stopping...", | |
| "realtime_not_found": "No realtime found!", | |
| "realtime": "Realtime", | |
| "realtime_markdown": "## Realtime Conversion", | |
| "realtime_markdown_2": "Realtime voice conversion", | |
| "realtime_latency": "Realtime latency", | |
| "realtime_not_startup": "Realtime not started", | |
| "monitor": "Use monitor", | |
| "exclusive_mode": "Exclusive Mode", | |
| "vad_enabled": "VAD voice detection", | |
| "audio_device": "Audio device", | |
| "input_audio_device_label": "Input audio device", | |
| "output_audio_device_label": "Output audio device", | |
| "monitor_output_device_label": "Playback audio device", | |
| "input_audio_device_info": "Input audio device, Recommended WASAPI or ASIO for low latency", | |
| "output_audio_device_info": "Output audio device, output audio device e.g. Speaker, headphone,...", | |
| "monitor_output_device_info": "Second output audio device for playback audio", | |
| "input_audio_gain_label": "Input gain", | |
| "output_audio_gain_label": "Output gain", | |
| "monitor_audio_gain_label": "Monitor gain", | |
| "input_audio_gain_info": "Input device gain", | |
| "output_audio_gain_info": "Output device gain", | |
| "monitor_audio_gain_info": "Monitor device gain", | |
| "input_asio_channels_label": "Input ASIO Channels", | |
| "output_asio_channels_label": "Output ASIO Channels", | |
| "monitor_asio_channels_label": "Monitor ASIO Channels", | |
| "input_asio_channels_info": "Input ASIO Audio Device Channel Number", | |
| "output_asio_channels_info": "Output ASIO Audio Device Channel Number", | |
| "monitor_asio_channels_info": "Monitor ASIO Audio Device Channel Number", | |
| "refresh_audio_device": "Refresh Device", | |
| "start_realtime_button": "Start Realtime", | |
| "stop_realtime_button": "Stop Realtime", | |
| "chunk_size": "Chunk size", | |
| "chunk_size_info": "Real-time conversion chunk size, value is (ms)", | |
| "silent_threshold_label": "Silence threshold", | |
| "silent_threshold_info": "Sound threshold for silence", | |
| "extra_convert_size_label": "Extra convert size", | |
| "extra_convert_size_info": "Extra convert size when converting to avoid resampling loss", | |
| "cross_fade_overlap_size_label": "Cross fade overlap size", | |
| "cross_fade_overlap_size_info": "Overlap level when combining output audio chunks", | |
| "vad_sensitivity_label": "VAD sensitivity", | |
| "vad_sensitivity_info": "VAD sensitivity. 0 is less sensitive, 3 is very sensitive.", | |
| "vad_frame_ms_label": "VAD frame Size", | |
| "vad_frame_ms_info": "VAD frame size processed for VAD (ms).", | |
| "training_sr": "The model's sampling rate ({sr_1} Hz) differs from the audio file's sampling rate ({sr_2} Hz).", | |
| "not_found_dataset": "No training audio files found!", | |
| "not_enough_data": "There is not enough data in the training dataset!", | |
| "using_reference": "Using reference {reference_name}!", | |
| "split_audio_mode": "Audio Splitting Mode", | |
| "split_audio_mode_info": "The splitter used to process audio files.", | |
| "normalization_mode": "Normalization", | |
| "normalization_mode_info": "Normalize the loudness of the training data.", | |
| "chunk_length": "Chunk Length (s)", | |
| "chunk_length_info": "The duration of each audio segment for the 'Simple' method.", | |
| "overlap_length": "Overlap Length", | |
| "overlap_length_info": "The overlapping duration between slices for the 'Simple' method.", | |
| "start_create_reference": "Starting to create the training reference set...", | |
| "create_reference": "Create Reference", | |
| "create_reference_success": "Successfully created the training reference set in {elapsed_time} seconds.", | |
| "create_reference_markdown": "## Create Training Reference", | |
| "create_reference_markdown_2": "Create reference for quality assurance when training models via TensorBoard.", | |
| "reference_name": "Reference Name", | |
| "reference_name_info": "The name assigned to the output reference set used.", | |
| "reference_info": "Create Reference Info", | |
| "custom_reference": "Custom Reference", | |
| "not_found_reference": "No reference set found. Custom reference set will not be used!", | |
| "alpha_label": "Blending Level of Methods", | |
| "alpha_info": "The blending ratio of pitch values extracted by different methods.", | |
| "multiscale_mel_loss": "Use Multi-Scale Mel Loss", | |
| "multiscale_mel_loss_info": "Compares the Mel spectrograms of real and generated audio at multiple scales. Helps the model learn timbral details, brightness, and frequency structure more effectively, thereby improving output speech quality and naturalness.", | |
| "realtime_client": "Realtime (Client)", | |
| "media_devices": "Browser does not support accessing audio devices via API", | |
| "mic_inaccessible": "Unable to access input devices!", | |
| "ws_connected": "Connected to [WS]", | |
| "ws_closed": "Stopped connecting to [WS]", | |
| "ws_disconnected": "Disconnected from [WS]" | |
| } |