数据集:

3AAISHELL-2 3Acityscapes 3AEuroparl-ASR-(EN) 3Afacebook/multilingual_librispeech 3AFisher 3Afisher_corpus 3Aimagenet_1k 3Alibrispeech_asr 3Aljspeech 3AMLCommons/peoples_speech 3Amozilla-foundation/common_voice_10_0 3Amozilla-foundation/common_voice_11_0 3Amozilla-foundation/common_voice_7_0 3Amozilla-foundation/common_voice_8_0 3AMultilingual-LibriSpeech 3AMultilingual-LibriSpeech-(2000-hours) 3Amultilingual_librispeech 3ANational-Singapore-Corpus-Part-1 3ANational-Singapore-Corpus-Part-6 3Ared_caps 3ARussian-LibriSpeech 3ASberDevices/Golos 3Ascene_parse_150 3ASOVA-Dataset 3Aspgi 3ASRE(2004-2010) 3Aswitchboard 3ASwitchboard-1 3Athe_pile 3Avctk 3AVOXCELEB-1 3AVOXCELEB-2 3AVoxPopuli 3AVoxPopuli-(DE) 3AVoxPopuli-(EN) 3AWSJ-0 3AWSJ-1 AISHELL-2 cityscapes Europarl-ASR-(EN) facebook/multilingual_librispeech Fisher fisher_corpus imagenet_1k librispeech_asr ljspeech MLCommons/peoples_speech mozilla-foundation/common_voice_10_0 mozilla-foundation/common_voice_7_0 mozilla-foundation/common_voice_8_0 Multilingual-LibriSpeech Multilingual-LibriSpeech-(2000-hours) multilingual_librispeech National-Singapore-Corpus-Part-1 National-Singapore-Corpus-Part-6 red_caps Russian-LibriSpeech SberDevices/Golos scene_parse_150 SOVA-Dataset SRE(2004-2010) switchboard Switchboard-1 the_pile vctk VOXCELEB-1 VOXCELEB-2 VoxPopuli VoxPopuli-(DE) VoxPopuli-(EN) WSJ-0 WSJ-1

预印本库:

arxiv:1808.10583 arxiv:1909.08053 arxiv:2002.05202 arxiv:2005.08100 arxiv:2006.06873 arxiv:2010.05646 arxiv:2101.00027 arxiv:2104.01721 arxiv:2104.09864 arxiv:2105.15203 arxiv:2108.10447 arxiv:2202.11094 arxiv:2305.05084

其他:

audio AutoTrain Compatible causal-lm Citrinet Conformer CTC FastConformer GAN groupvit hf-asr-leaderboard Eval Results Riva segformer speaker speaker-diarization speaker-recognition speaker-verification speech text generation text+generation titanet Transducer Transformer vision Vocoder

任务:

自动语音识别 特征提取 图像分类 图像分割 文本转语音 文生文

语言:

de en es fr ru uk zh

许可:

cc-by-4.0 other

类库:

NeMo PyTorch TensorFlow Transformers