SpeechBrain is an open-source and all-in-one conversational AI toolkit based on PyTorch.
sgmse-voicebankasr-conformer-loquaciousspkrec-ecapa-voxcelebasr-crdnn-switchboardasr-transformer-commonvoice-14-frlang-id-voxlingua107-ecapaasr-streaming-conformer-gigaspeechasr-crdnn-transformerlm-librispeechemotion-recognition-wav2vec2-IEMOCAPsoundchoice-g2pasr-transformer-aishellfocalnet-base-esc50vit-base-esc50asr-streaming-conformer-librispeechemotion-diarization-wavlm-largetts-fastspeech2-internal-alignment-ljspeechasr-transducer-commonvoice-14-frasr-transducer-commonvoice-14-deasr-transducer-commonvoice-14-itasr-wav2vec2-commonvoice-rwtts-mstacotron2-librittsspkrec-resnet-voxcelebasr-crdnn-commonvoice-14-rwasr-crdnn-commonvoice-14-estts-hifigan-ljspeechtts-diffwave-ljspeechtts-hifigan-libritts-16kHztts-hifigan-libritts-22050Hztts-fastspeech2-ljspeechPIQ-ESC50cnn14-esc50sepformer_rescuespeechasr-conformer-transformerlm-ksponspeechsepformer-libri3mixsepformer-libri2mixsepformer-wham16k-enhancementsepformer-wham-enhancementsepformer-whamr-enhancementresepformer-wsj02mixspkrec-xvect-voxcelebs2st-transformer-fr-en-hubert-l6-k100-cvssasr-crdnn-commonvoice-frasr-crdnn-commonvoice-itasr-crdnn-commonvoice-desepformer-wsj03mixsepformer-whamr16kREAL-M-sisnr-estimatorsepformer-dns4-16k-enhancementSLU-direct-SLURP-hubert-encasr-transformer-switchboard