연구할 때 많은 도움을 받은 SpeechBrain이 많은 발전을 이뤘다.
복습을 하면서 시리즈로 사용법을 한번 정리하려 한다.
오늘은 Github과 홈페이지의 내용을 정리하면서 SpeechBrain을 소개한다.
앞으로 설치법 부터 튜토리얼, 커스텀 데이터에 적용 등 여러가지를 다룰 예정입니다.
python train.py hparams/train.yaml100개 이상의 사전학습된 모델이 HuggingFace에 공개되어 있다.
각 모델은 유저 친화적인 인터페이스로 사용할 수 있다. 예를 들면 사전학습된 모델로 음성을 전사하는 것은 3줄으로 가능하다.
from speechbrain.pretrained import EncoderDecoderASR
asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-conformer-transformerlm-librispeech", savedir="pretrained_models/asr-transformer-transformerlm-librispeech")
asr_model.transcribe_file("speechbrain/asr-conformer-transformerlm-librispeech/example.wav")
별도 포스팅 예정입니다.
| Tasks | Datasets | Technologies/Models |
|---|---|---|
| Speech Recognition | AISHELL-1, CommonVoice, DVoice, KsponSpeech, LibriSpeech, MEDIA, RescueSpeech, Switchboard, TIMIT, Tedlium2, Voicebank | CTC, Tranducers, Transformers, Seq2Seq, Beamsearch techniques for CTC,seq2seq,transducers), Rescoring, Conformer, Branchformer, Hyperconformer, Kaldi2-FST |
| Speaker Recognition | VoxCeleb | ECAPA-TDNN, ResNET, Xvectors, PLDA, Score Normalization |
| Speech Separation | WSJ0Mix, LibriMix, WHAM!, WHAMR!, Aishell1Mix, BinauralWSJ0Mix | SepFormer, RESepFormer, SkiM, DualPath RNN, ConvTasNET |
| Speech Enhancement | DNS, Voicebank | SepFormer, MetricGAN, MetricGAN-U, SEGAN, spectral masking, time masking |
| Text-to-Speech | LJSpeech, LibriTTS | Tacotron2, Zero-Shot Multi-Speaker Tacotron2, FastSpeech2 |
| Vocoding | LJSpeech, LibriTTS | HiFiGAN, DiffWave |
| Spoken Language Understanding | MEDIA, SLURP, Fluent Speech Commands, Timers-and-Such | Direct SLU, Decoupled SLU, Multistage SLU |
| Speech-to-Speech Translation | CVSS | Discrete Hubert, HiFiGAN, wav2vec2 |
| Speech Translation | Fisher CallHome (Spanish), IWSLT22(lowresource) | wav2vec2 |
| Emotion Classification | IEMOCAP, ZaionEmotionDataset | ECAPA-TDNN, wav2vec2, Emotion Diarization |
| Language Identification | VoxLingua107, CommonLanguage | ECAPA-TDNN |
| Voice Activity Detection | LibriParty | CRDNN |
| Sound Classification | ESC50, UrbanSound | CNN14, ECAPA-TDNN |
| Self-Supervised Learning | CommonVoice, LibriSpeech | wav2vec2 |
| Interpretabiliy | ESC50 | Learning-to-Interpret (L2I), Non-Negative Matrix Factorization (NMF), PIQ |
| Speech Generation | AudioMNIST | Diffusion, Latent Diffusion |
| Metric Learning | REAL-M, Voicebank | Blind SNR-Estimation, PESQ Learning |
| Allignment | TIMIT | CTC, Viterbi, Forward Forward |
| Diarization | AMI | ECAPA-TDNN, X-vectors, Spectral Clustering |
| Tasks | Datasets | Technologies/Models |
|---|---|---|
| Language Modeling | CommonVoice, LibriSpeech | n-grams, RNNLM, TransformerLM |
| Response Generation | MultiWOZ | GPT2, Llama2 |
| Grapheme-to-Phoneme | LibriSpeech | RNN, Transformer, Curriculum Learning, Homograph loss |
SpeechBrain은 Conversational AI 기술 개발을 도와주기 위한 여러 기초 기능을 포함합니다.
@misc{speechbrain,
title={{SpeechBrain}: A General-Purpose Speech Toolkit},
author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
year={2021},
eprint={2106.04624},
archivePrefix={arXiv},
primaryClass={eess.AS},
note={arXiv:2106.04624}
}
SpeechBrain Hompage
Github