hugging_tools/sources/audio_models.txt

tts: ['speechbrain/tts-tacotron2-ljspeech', 'facebook/fastspeech2-en-ljspeech', 'espnet/kan-bayashi_ljspeech_joint_finetune_conformer_fastspeech2_hifigan', 'facebook/fastspeech2-en-200_speaker-cv4', 'Voicemod/fastspeech2-en-200_speaker-cv4', 'espnet/english_male_ryanspeech_fastspeech2', 'Voicemod/fastspeech2-en-male1', 'espnet/kan-bayashi_ljspeech_vits', 'Voicemod/fastspeech2-en-ljspeech', 'espnet/kan-bayashi_ljspeech_tacotron2', 'mio/tokiwa_midori', 'mio/amadeus', 'mio/Artoria']
automatic-speech-recognition:['openai/whisper-large-v2', 'openai/whisper-base', 'jonatasgrosman/wav2vec2-large-xlsr-53-english', 'openai/whisper-medium', 'facebook/wav2vec2-base-960h', 'facebook/wav2vec2-large-960h-lv60-self', 'facebook/s2t-small-librispeech-asr', 'openai/whisper-tiny', 'openai/whisper-tiny.en']
audio-to-audio:['JorisCos/DCCRNet_Libri1Mix_enhsingle_16k', 'speechbrain/sepformer-wham', 'facebook/xm_transformer_unity_hk-en', 'facebook/xm_transformer_sm_all-en']
audio-classification: ['ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition', 'harshit345/xlsr-wav2vec-speech-emotion-recognition', 'speechbrain/lang-id-voxlingua107-ecapa', 'anton-l/sew-mid-100k-ft-keyword-spotting', 'anton-l/wav2vec2-base-lang-id', 'anton-l/wav2vec2-random-tiny-classifier', 'superb/wav2vec2-base-superb-er', 'superb/hubert-large-superb-er', 'superb/wav2vec2-base-superb-sid', 'speechbrain/spkrec-xvect-voxceleb', 'MIT/ast-finetuned-audioset-10-10-0.4593', 'audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim', 'TalTechNLP/voxlingua107-epaca-tdnn', 'speechbrain/lang-id-commonlanguage_ecapa', 'speechbrain/urbansound8k_ecapa', 'sahita/language-identification', 'bookbot/wav2vec2-adult-child-cls', 'anton-l/wav2vec2-base-ft-keyword-spotting', 'hackathon-pln-es/wav2vec2-base-finetuned-sentiment-mesd', 'superb/wav2vec2-base-superb-ks', 'superb/hubert-base-superb-er', 'hackathon-pln-es/wav2vec2-base-finetuned-sentiment-classification-MESD']