You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/examples/librispeech
tianhao zhang 19180d359d
format wav2vec2 demo
2 years ago
..
asr0 fix s2t gpu training hang 2 years ago
asr1 fix s2t gpu training hang 2 years ago
asr2 fix s2t gpu training hang 2 years ago
asr3 support wav2vec2ASR on librispeech 2 years ago
.gitignore E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
README.md format wav2vec2 demo 2 years ago

README.md

ASR

  • asr0 - deepspeech2 Streaming/Non-Streaming
  • asr1 - transformer/conformer Streaming/Non-Streaming
  • asr2 - transformer/conformer Streaming/Non-Streaming with Kaldi feature
  • asr3 - wav2vecASR, ASR model with pre-trained wav2vec2 and CTC

Data

Data Subset Duration in Seconds
data/manifest.train 0.83s ~ 29.735s
data/manifest.dev 1.065 ~ 35.155s
data/manifest.test-clean 1.285s ~ 34.955s