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

minor fixes in the CTC decoding code (#1338)

Browse Source
This commit is contained in:
zr_jin 2023-10-25 17:14:17 +08:00 committed by GitHub
parent dcbc7a63e1
commit 770c495484
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
egs/multi_zh-hans/ASR/RESULTS.md
View File

@ -33,8 +33,8 @@ Character Error Rates (CERs) listed below are produced by the checkpoint of the
| Datasets | aidatatang _200zh | aidatatang _200zh | alimeeting | alimeeting | aishell-1 | aishell-1 | aishell-2 | aishell-2 | aishell-4 | magicdata | magicdata | kespeech-asr | kespeech-asr | kespeech-asr | WenetSpeech | WenetSpeech | WenetSpeech |
|--------------------------------|------------------------------|-------------|-------------------|--------------|----------------|-------------|------------------|-------------|------------------|------------------|-------------|-----------------------|-----------------------|-------------|--------------------|-------------------------|---------------------|
| Zipformer CER (%) | dev | test | eval| test | dev | test | dev| test | test | dev| test | dev phase1 | dev phase2 | test | dev | test meeting | test net |
| CTC Decoding | 14.57 | 15.26 | 72.85 | 69.70 | 12.87 | 13.76 | 23.56 | 25.55 | 71.75 | 22.35 | 19.34 | 42.38 | 26.90 | 48.71 | 64.88 | 67.29 | 54.24 |
| Zipformer CER (%) | dev | test | eval | test | dev | test | dev | test | test | dev | test | dev phase1 | dev phase2 | test | dev | test meeting | test net |
| CTC Decoding | 2.86 | 3.36 | 22.93 | 24.28 | 2.05 | 2.27 | 3.33 | 3.82 | 15.45 | 3.49 | 2.77 | 6.90 | 2.85 | 8.29 | 9.41 | 6.92 | 8.57 |
| Greedy Search | 3.36 | 3.83 | 23.90 | 25.18 | 2.77 | 3.08 | 3.70 | 4.04 | 16.13 | 3.77 | 3.15 | 6.88 | 3.14 | 8.08 | 9.04 | 7.19 | 8.17 |
Pre-trained model can be found here : https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-ctc-2023-10-24/

3
egs/multi_zh-hans/ASR/zipformer/ctc_decode.py
View File

@ -379,7 +379,8 @@ def decode_dataset(
this_batch = []
assert len(hyps) == len(texts)
for cut_id, hyp_words, ref_text in zip(cut_ids, hyps, texts):
ref_words = ref_text.split()
ref_words = list(ref_text.replace(" ", ""))
hyp_words = list("".join(hyp_words))
this_batch.append((cut_id, ref_words, hyp_words))
results[name].extend(this_batch)