mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,216 Commits 5 Branches 3 Tags
Commit Graph

31 Commits

Author SHA1 Message Date
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
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
242002e0bd
Strengthened style constraints (#1527) 2024-03-04 23:28:04 +08:00
Karel Vesely
716b82cc3a
streaming_decode.py, relax the audio range from [-1,+1] to [-10,+10] (#1448) 
- some AudioTransform classes produce audio signals out of range [-1,+1]
   - Resample produced 1.0079
   - The range [-10,+10] was chosen to still be able to reliably
     distinguish from the [-32k,+32k] signal...
- this is related to : https://github.com/lhotse-speech/lhotse/issues/1254
 2024-01-05 10:21:27 +08:00
Fangjun Kuang
8136ad775b
Use high_freq -400 in computing fbank features. (#1447) 
See also https://github.com/k2-fsa/sherpa-onnx/issues/514
 2024-01-04 13:59:32 +08:00
Fangjun Kuang
666d69b20d
Rename train2.py to avoid confusion (#1386) 2023-11-17 18:12:59 +08:00
zr_jin
ef658d691e
fixes for init value of diagnostics.TensorDiagnosticOptions (#1269) 
* fixes for `diagnostics`

Replace `2 ** 22` with `512` as the default value of `diagnostics.TensorDiagnosticOptions`

also black formatted some scripts

* fixed formatting issues
 2023-09-24 17:06:47 +08:00
Fangjun Kuang
34e40a86b3
Fix exporting decoder model to onnx (#1264) 
* Use torch.jit.script() to export the decoder model

See also https://github.com/k2-fsa/sherpa-onnx/issues/327
 2023-09-22 09:57:15 +08:00
Fangjun Kuang
f5dc957d44
Fix CI tests (#1266) 2023-09-21 21:16:14 +08:00
zr_jin
a81396b482
Use tokens.txt to replace bpe.model (#1162) 2023-08-12 16:53:59 +08:00
Fangjun Kuang
7b0afbdc16
Remove cur_batch_idx (#1102) 2023-05-30 14:49:54 +08:00
Zengwei Yao
8070258ec5
fix conv_emformer2, when using right_context_length=0 (#1076) 2023-05-21 20:31:54 +08:00
Fangjun Kuang
f5de2e90c6
Fix style issues. (#937) 2023-03-08 22:56:04 +08:00
pehonnet
07243d136a
remove key from result filename (#936) 
Co-authored-by: pe-honnet <pe.honnet@telepathy.ai>
 2023-03-08 21:06:07 +08:00
Fangjun Kuang
c5e687ddf5
Export streaming zipformer to ncnn (#906) 2023-02-13 23:41:43 +08:00
Fangjun Kuang
2b995639b7
Add ONNX support for Zipformer and ConvEmformer (#884) 2023-02-09 00:02:38 +08:00
Fangjun Kuang
c05f5d76df
fix decoding for ncnn (#828) 2023-01-10 20:52:13 +08:00
kobenaxie
9a9c5a0f9b
remove unused codes. (#821) 2023-01-06 11:16:22 +08:00
kobenaxie
6d659f423d
delete duplicate line for encoder initial state (#765) 2022-12-15 20:42:07 +08:00
Daniil
b293db4baf
Tedlium3 conformer ctc2 (#696) 
* modify preparation

* small refacor

* add tedlium3 conformer_ctc2

* modify decode

* filter unk in decode

* add scaling converter

* address comments

* fix lambda function lhotse

* add implicit manifest shuffle

* refactor ctc_greedy_search

* import model arguments from train.py

* style fix

* fix ci test and last style issues

* update RESULTS

* fix RESULTS numbers

* fix label smoothing loss

* update model parameters number in RESULTS
 2022-12-13 16:13:26 +08:00
Fangjun Kuang
f13cf61b05
Convert conv-emformer to ncnn (#717) 
* Export conv-emformer via torch.jit.trace()
 2022-12-06 16:34:27 +08:00
huangruizhe
6693d907d3
shuffle full Librispeech data (#574) 
* shuffled full/partial librispeech data

* fixed the code style issue

* Shuffled full librispeech data off-line

* Fixed style, addressed comments, and removed redandunt codes

* Used the suggested version of black

* Propagated the changes to other folders for librispeech (except
conformer_mmi and streaming_conformer_ctc)
 2022-11-27 11:26:09 +08:00
Desh Raj
d31db01037 manual correction of black formatting 2022-11-17 14:18:05 -05:00
Desh Raj
107df3b115 apply black on all files 2022-11-17 09:42:17 -05:00
Fangjun Kuang
60317120ca
Revert "Apply new Black style changes" 2022-11-17 20:19:32 +08:00
Desh Raj
d110b04ad3 apply new black formatting to all files 2022-11-16 13:06:43 -05:00
Fangjun Kuang
d1f16a04bd
fix type hints for decode.py (#623) 2022-10-18 06:56:12 +08:00
Wei Kang
5c17255eec
Sort results to make it more convenient to compare decoding results (#522) 
* Sort result to make it more convenient to compare decoding results

* Add cut_id to recognition results

* add cut_id to results for all recipes

* Fix torch.jit.script

* Fix comments

* Minor fixes

* Fix torch.jit.tracing for Pytorch version before v1.9.0
 2022-08-12 07:12:50 +08:00
Zengwei Yao
8203d10be7
Add stats about duration and padding proportion (#485) 
* add stats about duration and padding proportion

* add  for utt_duration

* add stats for other recipes

* add stats for other 2 recipes

* modify doc

* minor change
 2022-07-25 16:40:43 +08:00
Zengwei Yao
bc2882ddcc
Simplified memory bank for Emformer (#440) 
* init files

* use average value as memory vector for each chunk

* change tail padding length from right_context_length to chunk_length

* correct the files, ln -> cp

* fix bug in conv_emformer_transducer_stateless2/emformer.py

* fix doc in conv_emformer_transducer_stateless/emformer.py

* refactor init states for stream

* modify .flake8

* fix bug about memory mask when memory_size==0

* add @torch.jit.export for init_states function

* update RESULTS.md

* minor change

* update README.md

* modify doc

* replace torch.div() with <<

* fix bug, >> -> <<

* use i&i-1 to judge if it is a power of 2

* minor fix

* fix error in RESULTS.md
 2022-07-12 19:19:58 +08:00