Facebook AI Research Sequence-to-Sequence Toolkit written .zip

# wav2vec 2.0 wav2vec 2.0 learns speech representations on unlabeled data as described in [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (Baevski et al., 2020)](https://arxiv.org/abs/2006.11477). We learned speech representations in multiple languages as well in [Unsupervised Cross-lingual Representation Learning for Speech Recognition (Conneau et al., 2020)](https://arxiv.org/abs/2006.13979). We also combined wav2vec 2.0 with self-training in [Self-training and Pre-training are Complementary for Speech Recognition (Xu et al., 2020)](https://arxiv.org/abs/2010.11430). We combined speech data from multiple domains in [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training (Hsu, et al., 2021)](https://arxiv.org/abs/2104.01027). We finetuned XLSR-53 on multiple languages to transcribe unseen languages in [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition (Xu et al., 2021)](https://arxiv.org/abs/2109.11680). ## Pre-trained models Model | Finetuning split | Dataset | Model |---|---|---|--- Wav2Vec 2.0 Base | No finetuning | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_small.pt) Wav2Vec 2.0 Base | 10 minutes | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_small_10m.pt) Wav2Vec 2.0 Base | 100 hours | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_small_100h.pt) Wav2Vec 2.0 Base | 960 hours | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_small_960h.pt) Wav2Vec 2.0 Large | No finetuning | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/libri960_big.pt) Wav2Vec 2.0 Large | 10 minutes | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_big_10m.pt) Wav2Vec 2.0 Large | 100 hours | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_big_100h.pt) Wav2Vec 2.0 Large | 960 hours | [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_big_960h.pt) Wav2Vec 2.0 Large (LV-60)* | No finetuning | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_new.pt) Wav2Vec 2.0 Large conformer - rel_pos (LV-60)* | No finetuning | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_relpos_PT_no_FT) Wav2Vec 2.0 Large conformer - rope (LV-60)* | No finetuning | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_rope_PT_no_FT) Wav2Vec 2.0 Large (LV-60)* | 10 minutes | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_10m_new.pt) Wav2Vec 2.0 Large (LV-60)* | 100 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_100h_new.pt) Wav2Vec 2.0 Large conformer - rel_pos (LV-60)* | 100 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_relpos_PT_100h_FT.pt) Wav2Vec 2.0 Large conformer - rope (LV-60)* | 100 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_rope_PT_100h_FT.pt) Wav2Vec 2.0 Large (LV-60)* | 960 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec2_vox_960h_new.pt) Wav2Vec 2.0 Large conformer - rel_pos (LV-60)* | 960 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_relpos_PT_960h_FT.pt) Wav2Vec 2.0 Large conformer - rope (LV-60)* | 960 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) | [download](s3://dl.fbaipublicfiles.com/fairseq/conformer/wav2vec2/librilight/LL_rope_PT_960h_FT.pt) Wav2Vec 2.0 Large (LV-60) + Self Training * | 10 minutes | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_10m_pl.pt) Wav2Vec 2.0 Large (LV-60) + Self Training * | 100 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_100h_pl.pt) Wav2Vec 2.0 Large (LV-60) + Self Training * | 960 hours | [Libri-Light](https://github.com/facebookresearch/libri-light) + [Librispeech](http://www.openslr.org/12) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_960h_pl.pt) Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) ** | No finetuning | [Libri-Light](https://github.com/facebookresearch/libri-light) + [CommonVoice](https://commonvoice.mozilla.org/en/languages) + [Switchboard](https://catalog.ldc.upenn.edu/LDC97S62) + [Fisher](https://catalog.ldc.upenn.edu/LDC2004T19) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/w2v_large_lv_fsh_swbd_cv.pt) Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) ** | 960 hours Librispeech | [Libri-Light](https://github.com/facebookresearch/libri-light) + [CommonVoice](https://commonvoice.mozilla.org/en/languages) + [Switchboard](https://catalog.ldc.upenn.edu/LDC97S62) + [Fisher](https://catalog.ldc.upenn.edu/LDC2004T19) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/w2v_large_lv_fsh_swbd_cv_ftls960_updated.pt) Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) ** | 300 hours Switchboard | [Libri-Light](https://github.com/facebookresearch/libri-light) + [CommonVoice](https://commonvoice.mozilla.org/en/languages) + [Switchboard](https://catalog.ldc.upenn.edu/LDC97S62) + [Fisher](https://catalog.ldc.upenn.edu/LDC2004T19) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/w2v_large_lv_fsh_swbd_cv_ftsb300_updated.pt) \* updated (Oct. 24, 2020)\ ** updated (Nov. 13, 2021) We also release multilingual pre-trained wav2vec 2.0 (XLSR) models: Model | Architecture | Hours | Languages | Datasets | Model |---|---|---|---|---|--- XLSR-53 | Large | 56k | 53 | MLS, CommonVoice, BABEL | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr_53_56k.pt) The XLSR model uses the following datasets for multilingual pretraining: * **[MLS: Multilingual LibriSpeech](https://indico2.conference4me.psnc.pl/event/35/contributions/3585/attachments/1060/1101/Wed-2-6-10.pdf)** (8 languages, 50.7k hours): *Dutch, English, French, German, Italian, Polish, Portuguese, Spanish* * **[CommonVoice](https://commonvoice.mozilla.org/en/languages)** (36 languages, 3.6k hours): *Arabic, Basque, Breton, Chinese (CN), Chinese (HK), Chinese (TW), Chuvash, Dhivehi, Dutch, English, Esperanto, Estonian, French, German, Hakh-Chin, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kinyarwanda, Kyrgyz, Latvian, Mongolian, Persian, Portuguese, Russian, Sakha, Slovenian, Spanish, Swedish, Tamil, Tatar, Turkish, Welsh* (see also [finetuning splits]([https://dl.fbaipublicfiles.com/cpc_audio/common_voices_splits.tar.gz]) from [this paper](https://arxiv.org/abs/2002.02848)). * **[Babel](https://catalog.ldc.upenn.edu/byyear)** (17 languages, 1.7k hours): *Assamese, Bengali, Cantonese, Cebuano, Georgian, Haitian, Kazakh, Kurmanji, Lao, Pashto, Swahili, Tagalog, Tamil, Tok, Turkish, Vietnamese, Zulu* We also finet