o jq?@sZddlZddlZddlZddlmZddlmZdZddZddZe d kr+edSdS) N)RawTextHelpFormatter)Patha Synthesize speech on command line. You can either use your trained model or choose a model from the provided list. If you don't specify any models, then it uses LJSpeech based English model. #### Single Speaker Models - List provided models: ``` $ tts --list_models ``` - Get model info (for both tts_models and vocoder_models): - Query by type/name: The model_info_by_name uses the name as it from the --list_models. ``` $ tts --model_info_by_name "///" ``` For example: ``` $ tts --model_info_by_name tts_models/tr/common-voice/glow-tts $ tts --model_info_by_name vocoder_models/en/ljspeech/hifigan_v2 ``` - Query by type/idx: The model_query_idx uses the corresponding idx from --list_models. ``` $ tts --model_info_by_idx "/" ``` For example: ``` $ tts --model_info_by_idx tts_models/3 ``` - Query info for model info by full name: ``` $ tts --model_info_by_name "///" ``` - Run TTS with default models: ``` $ tts --text "Text for TTS" --out_path output/path/speech.wav ``` - Run TTS and pipe out the generated TTS wav file data: ``` $ tts --text "Text for TTS" --pipe_out --out_path output/path/speech.wav | aplay ``` - Run a TTS model with its default vocoder model: ``` $ tts --text "Text for TTS" --model_name "///" --out_path output/path/speech.wav ``` For example: ``` $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --out_path output/path/speech.wav ``` - Run with specific TTS and vocoder models from the list: ``` $ tts --text "Text for TTS" --model_name "///" --vocoder_name "///" --out_path output/path/speech.wav ``` For example: ``` $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --vocoder_name "vocoder_models/en/ljspeech/univnet" --out_path output/path/speech.wav ``` - Run your own TTS model (Using Griffin-Lim Vocoder): ``` $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav ``` - Run your own TTS and Vocoder models: ``` $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json ``` #### Multi-speaker Models - List the available speakers and choose a among them: ``` $ tts --model_name "//" --list_speaker_idxs ``` - Run the multi-speaker TTS model with the target speaker ID: ``` $ tts --text "Text for TTS." --out_path output/path/speech.wav --model_name "//" --speaker_idx ``` - Run your own multi-speaker TTS model: ``` $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/model.pth --config_path path/to/config.json --speakers_file_path path/to/speaker.json --speaker_idx ``` ### Voice Conversion Models ``` $ tts --out_path output/path/speech.wav --model_name "//" --source_wav --target_wav ``` cCs8t|tr|S|dvrdS|dvrdStd)N)yestruety1T)nofalsefn0FzBoolean value expected.) isinstanceboollowerargparseArgumentTypeError)vrE/home/kuhnn/.local/lib/python3.10/site-packages/TTS/bin/synthesize.pystr2bools    rcCs|tjtddtd}|jdtddddd |jd tdd d |jd tddd |jdtddd |jdtddd |jdtddd |jddtdd|jdtddd |jdtddd |jdtddd |jd!td"d#d |jd$td%dd |jd&td'dd |jd(td)dd |jd*td+dd |jd,d-tdddd.|jd/td0dd |jd1td2dd |jd3td4dd |jd5td6dd |jd7d8d9dd:|jd;dtd?dd |jd@tdAdd |jdBdCtdddd.|jdDdEtdddd.|jdFtdGdd |jdHtdIdd |jdJtdKdd |jdLtdMdd |jdNtddOd |jdPtddQd |jdRtddSd | }|j |j |j |j |j|j|j|j|jg }t|s^| dTg|jretjnd}t|jrodntjdUdVlm}dUdWlm}dUdXlm}tt j!dY}|||j"dZ}|} d} d} d} d} d}d}d}d}d}d}d}|j r| t#|jr|j}||t#|jr|j}|$|t#|j%dur0|j&s0|'|j%\}}}|d[d\kr |} |} d]|vr |j(dur|d]n|j(|_(|d[d^kr|}|}|)d_dd`ks't*|dat+r0|}d} d} d|_(|j(durC|j,sC|'|j(\}}}|j&durU|j&} |j-} |j.} |j/} |j,dura|j,}|j0}|j1durm|j1}|j2}|j3}|j4rvdb}|| | | | ||||||||j5 6|}|j rt7dct7|j8j9j: WddS|j rt7ddt7|j8j;j: WddS|j<r|j=s|j>st7de WddS|j rt7df?|j | dur|j@|j |j=|jA|j>|j|jB|jC|jDdg}n!|dur|jE|j|jdh}n|dur|j@|j |j=|jA|j>di}t7dj?|jF|jG||jF|dkWddS1s7wYdS)lNz ``` ) descriptionformatter_classz --list_models?TFz2list available pre-trained TTS and vocoder models.)typenargsconstdefaulthelpz--model_info_by_idxz=model info using query format: /)rrrz--model_info_by_namezMmodel info using query format: ///z--textzText to generate speech.z --model_namez$tts_models/en/ljspeech/tacotron2-DDCzUName of one of the pre-trained TTS models in format //z--vocoder_namezZName of one of the pre-trained vocoder models in format //z --config_pathzPath to model config file.)rrrz --model_pathzPath to model file.z --out_pathztts_output.wavzOutput wav file path.z --use_cudazRun model on CUDA.)rrrz--devicezDevice to run model on.cpuz--vocoder_pathzPath to vocoder model file. If it is not defined, model uses GL as vocoder. Please make sure that you installed vocoder library before (WaveRNN).z--vocoder_config_pathz"Path to vocoder model config file.z--encoder_pathz#Path to speaker encoder model file.z--encoder_config_pathz$Path to speaker encoder config file.z --pipe_outz1stdout the generated TTS wav file for shell pipe.)rrrrrz--speakers_file_pathz"JSON file for multi-speaker model.z--language_ids_file_pathz"JSON file for multi-lingual model.z --speaker_idxz0Target speaker ID for a multi-speaker TTS model.z--language_idxz1Target language ID for a multi-lingual TTS model.z --speaker_wav+zwav file(s) to condition a multi-speaker TTS model with a Speaker Encoder. You can give multiple file paths. The d_vectors is computed as their average.)rrrz --gst_stylez&Wav path file for GST style reference.)rrz--capacitron_style_wavz/Wav path file for Capacitron prosody reference.z--capacitron_style_textzTranscription of the reference.z--list_speaker_idxsz?List available speaker ids for the defined multi-speaker model.z--list_language_idxsz@List available language ids for the defined multi-lingual model.z--save_spectogramzIIf true save raw spectogram for further (vocoder) processing in out_path.z--reference_wavzLReference wav file to convert in the voice of the speaker_idx or speaker_wavz--reference_speaker_idxzsspeaker ID of the reference_wav speaker (If not provided the embedding will be computed using the Speaker Encoder).z--progress_barzEIf true shows a progress bar for the model download. Defaults to Truez --source_wavz=Original audio file to convert in the voice of the target_wavz --target_wavz;Target audio file to convert in the voice of the source_wavz --voice_dirzVoice dir for tortoise modelz-hr)TTS) ModelManager) Synthesizerz../.models.json) progress_bar model_type tts_modelsdefault_vocodervoice_conversion_modelsauthorfairseq model_urlcudazh > Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model.zj > Available language ids: (Set --language_idx flag to one of these values to use the multi-lingual model.z [!] Looks like you use a multi-speaker model. Define `--speaker_idx` to select the target speaker. You can list the available speakers for this model by `--list_speaker_idxs`.z > Text: {}) speaker_name language_name speaker_wav reference_wav style_wav style_textreference_speaker_name) source_wav target_wav)r.r/r0z > Saving output to {})pipe_out)HrArgumentParserrreplacer add_argumentrstrr parse_argstext list_modelslist_speaker_idxslist_language_idxsr1model_info_by_idxmodel_info_by_namer5r6anyr7sysstdout contextlibredirect_stdoutTTS.apir"TTS.utils.manager#TTS.utils.synthesizerr$r__file__parentr%exitmodel_info_by_full_name model_name model_pathdownload_model vocoder_namegetrlist vocoder_path config_pathspeakers_file_pathlanguage_ids_file_pathvocoder_config_path encoder_pathencoder_config_pathdeviceuse_cuda voice_dirtoprint tts_modelspeaker_manager name_to_idlanguage_managertts_speakers_file speaker_idxr0formattts language_idxcapacitron_style_wavcapacitron_style_textreference_speaker_idxvoice_conversionout_pathsave_wav)parserargs check_argsr7r"r#r$pathmanagerapitts_pathtts_config_pathrWrXrUrYrZr[vc_pathvc_config_path model_dir model_querymodel_query_full_namerPrV model_item_r\ synthesizerwavrrrmainsL           "    ow   $r__main__) rrFrDrpathlibrrrr__name__rrrrs  z _