Open safarisadegh opened 5 months ago
could you upload the test waves?
test_wavs_1.zip (downloaded from this link )
@csukuangfj
did you test the files? @csukuangfj
Sorry, I missed it.
Could you tell me where you get decode_with_HLG.py
?
This mode https://huggingface.co/csukuangfj/icefall-asr-librispeech-conformer-ctc-jit-bpe-500-2021-11-09/tree/main
is from
https://github.com/k2-fsa/icefall/tree/master/egs/aishell/ASR/conformer_ctc
and there is no decode_with_HLG.py
inside the directory conformer_ctc
.
If you write decode_with_HLG.py
yourself, would you mind sharing it with us?
I got decode_with_HLG.py from links you have provided in Readme : https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/conformer_ctc/jit_pretrained_decode_with_HLG.py This is the file i have used: decode_with_HLG.zip
@csukuangfj
This is the procedure I have followed: first, i have converted HLG.pt to HLG.fst by running python3 convert-k2-to-openfst.py --olabels aux_labels ./lang_bpe_500/HLG.pt ./lang_bpe_500/HLG.fst
Please generate HLG.fst
with the following script
https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/local/prepare_lang_fst.py
Hi, I have tried to use your package to decode audio files with provided pre-trained model in icefall-asr-librispeech-conformer-ctc-jit-bpe-500- but sometimes i get error and sometimes the decoding result is wrong.
This is the procedure I have followed: first, i have converted HLG.pt to HLG.fst by running
python3 convert-k2-to-openfst.py --olabels aux_labels ./lang_bpe_500/HLG.pt ./lang_bpe_500/HLG.fst
then i used to decodet test_wavs using following command:
python3 decode_with_HLG.py --nn-model ./lang_bpe_500/cpu_jit.pt --HLG ./lang_bpe_500/HLG.fst --words ./lang_bpe_500/words.txt test_wavs_1089-134686-0001.wav test_wavs_1221-135766-0001.wav test_wavs_1221-135766-0002.wav
finally, this is the output:
What is wrong? Thanks for your contributions. @csukuangfj