Fangjun Kuang
8905ef5d59
Fix gigaspeech dataset iterator.
...
Previously, it was reset after every epoch, which may cause it to
always use the first part of the gigaspeech dataset if you choose
a small --giga-prob.
2025-11-28 10:51:21 +08:00
Karel Vesely
693f069de7
zipformer/ctc_align.py ( #2020 )
...
* zipformer/ctc_align.py
- tool for forced-alignment with CTC model
- provides timeline, computes per-token and per-utterance acoustic confidences
- based on torchaudio `forced_align()`
- confidences are computed in several ways
other modifications:
- LibriSpeechAsrDataModel extended with `::load_manifest()` to allow
passing-in cutset from CLI.
- update @custom_fwd @custom_bwd in scaling.py
- streaming_decode.py update errs/recogs/log filenames '-' <-> '_'
* putting back `custom_bwd`, `custom_fwd`
* integrating remarks from PR
* update of argparse help strings
* ctc_align.py, avoid shadowing a variable
* Finalizing the code:
- adding some coderabbit suggestions.
- removing `word_table`, `decoding_graph` from aligner API (unused)
- improved consistency of variable names (confidences)
- updated docstrings
2025-10-06 07:49:37 +08:00
Amir Hussein
729a5ba3ec
IWSLT-Ta ASR/ST ( #1362 )
...
This is a pull request for Dialectal IWSLT-Tunisian 2022 shared task https://iwslt.org/2022/dialect ASR and ST recipes.
2025-09-22 09:58:00 +08:00
Fangjun Kuang
34fc1fdf0d
Fix transformer decoder layer ( #1995 )
2025-07-18 20:12:29 +08:00
Fangjun Kuang
e22bc78f98
Export streaming zipformer2 to RKNN ( #1977 )
2025-07-11 13:24:01 +08:00
Teo Wen Shen
da87e7fc99
add weights_only=False to torch.load ( #1984 )
2025-07-10 15:27:08 +08:00
Yifan Yang
89728dd4f8
Refactor data preparation for GigaSpeech recipe ( #1986 )
2025-07-10 11:17:37 +08:00
Fangjun Kuang
fba5e67d5e
Fix CI tests. ( #1974 )
...
- Introduce unified AMP helpers (create_grad_scaler, torch_autocast) to handle
deprecations in PyTorch ≥2.3.0
- Replace direct uses of torch.cuda.amp.GradScaler and torch.cuda.amp.autocast
with the new utilities across all training and inference scripts
- Update all torch.load calls to include weights_only=False for compatibility with
newer PyTorch versions
2025-07-01 13:47:55 +08:00
Fangjun Kuang
71377d21cd
Export streaming zipformer models with whisper feature to onnx ( #1973 )
2025-06-30 19:01:15 +08:00
Wei Kang
343b8fa2dc
Using non strict match in context graph for contextual words ( #1952 )
2025-06-19 12:27:15 +08:00
Wei Kang
f80a2ee110
Decrease num_buckets & remove shuffle_buffer_size ( #1955 )
2025-06-19 12:26:37 +08:00
Zengwei Yao
ffb7d05635
refactor branch exchange in cr-ctc ( #1954 )
2025-05-27 12:09:59 +08:00
Tianxiang Zhao
30e7ea4b5a
Fix a bug in finetune.py --use-mux ( #1949 )
2025-05-22 12:05:01 +08:00
Yifan Yang
e79833aad2
ensure SwooshL/SwooshR output dtype matches input dtype ( #1940 )
2025-05-12 19:28:48 +08:00
Fangjun Kuang
171cf8c9fe
Avoid redundant computation in PiecewiseLinear. ( #1915 )
2025-04-09 11:52:37 +08:00
Fangjun Kuang
db9fb8ad31
Add scripts to export streaming zipformer(v1) to RKNN ( #1882 )
2025-02-27 17:10:58 +08:00
Han Zhu
ab91112909
Improve infinity-check ( #1862 )
...
1. Attach the inf-check hooks if the grad scale is getting too small.
2. Add try-catch to avoid OOM in the inf-check hooks.
3. Set warmup_start=0.1 to reduce chances of divergence
2025-01-09 15:05:38 +08:00
Seonuk Kim
8d602806c3
Update conformer.py ( #1859 )
...
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
Swich -? Swish
2025-01-06 17:31:13 +08:00
Seonuk Kim
3b6d54007b
Update conformer.py ( #1857 )
...
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
2025-01-06 13:17:02 +08:00
Han Zhu
48088cb807
Refactor optimizer ( #1837 )
...
* Print indexes of largest grad
2024-12-30 15:30:02 +08:00
Fangjun Kuang
d4d4f281ec
Revert "Replace deprecated pytorch methods ( #1814 )" ( #1841 )
...
This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.
2024-12-18 16:49:57 +08:00
Li Peng
3e4da5f781
Replace deprecated pytorch methods ( #1814 )
...
* Replace deprecated pytorch methods
- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)
* Replace `with autocast(...)` with `with autocast("cuda", ...)`
Co-authored-by: Li Peng <lipeng@unisound.ai>
2024-12-16 10:24:16 +08:00
zr_jin
87cadfcd2e
fixed formatting issue ( #1791 )
...
* isort fixed formatting issue
2024-10-30 21:14:12 +08:00
Wei Kang
d513d456b8
Add prefix beam search and corresponding decoding methods ( #1786 )
...
* Add prefix beam search / shallow fussion / hotwords in librispeech ctc decode
* Add librispeech cr-ctc prefix beam search results
2024-10-30 10:14:34 +08:00
Fangjun Kuang
05f756390c
Avoid using lr from checkpoint. ( #1781 )
2024-10-28 00:59:04 +08:00
zr_jin
88bacfb9e6
minor fixes for the repo ( #1775 )
...
* minor fixes for the repo
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2024-10-21 13:51:56 +08:00
zr_jin
e8b6b920c0
A LibriTTS recipe on both ASR & Neural Codec Tasks ( #1746 )
...
* added ASR & CODEC recipes for LibriTTS corpus
2024-10-21 11:30:14 +08:00
Zengwei Yao
693d84a301
Add Consistency-Regularized CTC ( #1766 )
...
* support consistency-regularized CTC
* update arguments of cr-ctc
* set default value of cr_loss_masked_scale to 1.0
* minor fix
* refactor codes
* update RESULTS.md
2024-10-21 10:35:26 +08:00
Zengwei Yao
fbba712887
Fix issue with eval mode in ActivationDropoutLinear ( #1770 )
...
* Fix issue with eval mode in ActivationDropoutLinear
---------
Co-authored-by: Daniel Povey <dpovey@gmail.com>
2024-10-12 19:09:05 +08:00
Fangjun Kuang
6f1abd832d
Fix exporting streaming zipformer models. ( #1755 )
2024-09-11 21:04:52 +08:00
Xiaoyu Yang
a6c02a4d8c
zipformer BF16 training recipe ( #1700 )
...
Support Zipformer AMP +BF16 training
2024-08-23 09:42:22 +08:00
Yuekai Zhang
3b434fe83c
fix triton onnx export ( #1730 )
2024-08-23 09:33:46 +08:00
Karel Vesely
1730fce688
split save_results() -> save_asr_output() + save_wer_results() ( #1712 )
...
- the idea is to support `--skip-scoring` argument passed to a decoding
script
- created for Transducer decoding (non-streaming, streaming)
- it can be done also for CTC decoding... (not yet)
- also added `--label` for extra label in `streaming_decode.py`
- and also added `set_caching_enabled(True)`, which has no effect on
librispeech, but it leads to faster runtime on DBs with long
recordings (assuming `librispeech/zipformer` scripts are the
example scripts for other setups)
2024-08-13 23:02:14 +08:00
zzasdf
11151415f3
fix error in accum_grad ( #1693 )
2024-07-17 17:47:43 +08:00
Zengwei Yao
d47c078286
add decoding method of ctc-greedy-search in zipformer recipe ( #1690 )
2024-07-14 17:30:13 +08:00
Zengwei Yao
334beed2af
fix usages of returned losses after adding attention-decoder in zipformer ( #1689 )
2024-07-12 16:50:58 +08:00
Teo Wen Shen
19048e155b
Cast grad_scale in whiten to float ( #1663 )
...
* cast grad_scale in whiten to float
* fix cast in zipformer_lora
2024-07-11 15:12:30 +08:00
Yifan Yang
d65187ec52
Small fix ( #1686 )
2024-07-11 14:45:35 +08:00
Zengwei Yao
785f3f0bcf
Update RESULTS.md, adding results and model links of zipformer-small/medium CTC/AED models ( #1683 )
2024-07-09 20:04:47 +08:00
zr_jin
2d64228efa
Update attention_decoder.py ( #1681 )
2024-07-06 09:01:34 +08:00
Zengwei Yao
f76afff741
Support CTC/AED option for Zipformer recipe ( #1389 )
...
* add attention-decoder loss option for zipformer recipe
* add attention-decoder-rescoring
* update export.py and pretrained_ctc.py
* update RESULTS.md
2024-07-05 20:19:18 +08:00
Yifan Yang
cbcac23d26
Fix typos, remove unused packages, normalize comments ( #1678 )
2024-07-04 14:19:45 +08:00
Manix
eaab2c819f
Zipformer Onnx FP16 ( #1671 )
...
Signed-off-by: manickavela29 <manickavela1998@gmail.com>
2024-06-27 16:08:24 +08:00
Fangjun Kuang
3059eb4511
Fix doc URLs ( #1660 )
2024-06-21 11:10:14 +08:00
Fangjun Kuang
b88062292b
Typo fixes ( #1643 )
2024-06-03 16:49:21 +08:00
Zengwei Yao
0df406c5da
Initialize BiasNorm bias with small random values ( #1630 )
2024-05-20 22:32:02 +08:00
zr_jin
68980c5d0a
Fix an error occured during mmi preparation ( #1626 )
...
* init commit
* updated
2024-05-17 19:45:15 +08:00
Dongji Gao
9a17f4ce41
add OTC related scripts using phone as units instead of BPEs ( #1602 )
...
* add otc related scripts using phone instead of bpe
2024-04-26 00:55:44 +08:00
zzasdf
25cabb7663
fix error in padding computing ( #1607 )
2024-04-25 22:40:07 +08:00
Yifan Yang
ed6bc200e3
Update train.py ( #1590 )
2024-04-11 19:35:25 +08:00
