7 Commits

Author	SHA1	Message	Date
Guanbo Wang	f293d4ade3	Update results	2022-05-12 00:57:02 -04:00
Guanbo Wang	239524d384	black	2022-05-03 22:26:46 +00:00
Guanbo Wang	c08c6ae0ec	gigaspeech decode	2022-05-03 22:15:55 +00:00
Guanbo Wang	d6390fd107	Update params	2022-04-21 02:30:54 -04:00
Guanbo Wang	2d07df5281	flake8	2022-04-17 02:01:21 +00:00
Guanbo Wang	713601c624	Copy RNN-T recipe from librispeech	2022-04-17 01:52:32 +00:00
Wang, Guanbo	5fe58de43c	GigaSpeech recipe (#120) ... * initial commit * support download, data prep, and fbank * on-the-fly feature extraction by default * support BPE based lang * support HLG for BPE * small fix * small fix * chunked feature extraction by default * Compute features for GigaSpeech by splitting the manifest. * Fixes after review. * Split manifests into 2000 pieces. * set audio duration mismatch tolerance to 0.01 * small fix * add conformer training recipe * Add conformer.py without pre-commit checking * lazy loading and use SingleCutSampler * DynamicBucketingSampler * use KaldifeatFbank to compute fbank for musan * use pretrained language model and lexicon * use 3gram to decode, 4gram to rescore * Add decode.py * Update .flake8 * Delete compute_fbank_gigaspeech.py * Use BucketingSampler for valid and test dataloader * Update params in train.py * Use bpe_500 * update params in decode.py * Decrease num_paths while CUDA OOM * Added README * Update RESULTS * black * Decrease num_paths while CUDA OOM * Decode with post-processing * Update results * Remove lazy_load option * Use default `storage_type` * Keep the original tolerance * Use split-lazy * black * Update pretrained model Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>	2022-04-14 16:07:22 +08:00