mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
5fe58de43c
* 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>
21 lines
524 B
INI
21 lines
524 B
INI
[flake8]
|
|
show-source=true
|
|
statistics=true
|
|
max-line-length = 80
|
|
per-file-ignores =
|
|
# line too long
|
|
egs/librispeech/ASR/*/conformer.py: E501,
|
|
egs/aishell/ASR/*/conformer.py: E501,
|
|
egs/tedlium3/ASR/*/conformer.py: E501,
|
|
egs/gigaspeech/ASR/*/conformer.py: E501,
|
|
egs/librispeech/ASR/pruned_transducer_stateless2/*.py: E501,
|
|
|
|
# invalid escape sequence (cause by tex formular), W605
|
|
icefall/utils.py: E501, W605
|
|
|
|
exclude =
|
|
.git,
|
|
**/data/**,
|
|
icefall/shared/make_kn_lm.py,
|
|
icefall/__init__.py
|