Use final_architecture1.pkl for live test

Question

Use final_architecture1.pkl for live test

spacecd opened this issue 3 years ago · 4 comments

Hi Sir,
Thanks for the detailed README.md, I managed to finish model training following Librispeech tutorial using libri_MLP_fmllr.cfg and got the result:
%WER 9.54 [ 5018 / 52576, 558 ins, 643 del, 3817 sub ] /pytorch-kaldi/repo/exp_torch/libri_MLP_fmllr_GPU_ c75_batch256/decode_test_clean_out_dnn1/wer_13_0.0,

I’d like to move the trained model exp_files/final_architecture1.pkl to one of our hardware recognition system for live test. Since our existing system loads final.mdl in Kaldi format, does anyone can give any idea for converting final_architecture1.pkl to Kaldi format? Thanks in advance :-D

Answer 1 · 2021-08-02T04:40:21.000Z

Hi, we aren't supporting pytorch-kaldi anymore because we now haveca much better toolkit called speechbrain. My suggestion is to switch to it.

…

On Sun, Aug 1, 2021, 11:59 PM spacecd ***@***.***> wrote: Hi Sir, Thanks for the detailed README.md, I managed to finish model training following Librispeech tutorial using libri_MLP_fmllr.cfg and got the result: %WER 9.54 [ 5018 / 52576, 558 ins, 643 del, 3817 sub ] /pytorch-kaldi/repo/exp_torch/libri_MLP_fmllr_GPU_ c75_batch256/decode_test_clean_out_dnn1/wer_13_0.0, I’d like to move the trained model exp_files/final_architecture1.pkl to one of our hardware recognition system for live test. Since our existing system loads final.mdl in Kaldi format, does anyone can give any idea for converting final_architecture1.pkl to Kaldi format? Thanks in advance :-D — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#255>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AEA2ZVX7RSXB5XM4IJ3XGK3T2YJYLANCNFSM5BL4QHRA> .

Answer 2 · 2021-08-02T05:22:01.000Z

Thanks Mirco for the reply.
I’ve heard the name of SpeechBrain in the community, and will start follow it :-D

A quick question, is it possible that we convert the ASR model trained by SpeechBrain to Kaldi format?
I ask this because our existing hardware recognition system is running C optimized kaldi decoder.

Hi, we aren't supporting pytorch-kaldi anymore because we now haveca much better toolkit called speechbrain. My suggestion is to switch to it.
…
On Sun, Aug 1, 2021, 11:59 PM spacecd @.***> wrote: Hi Sir, Thanks for the detailed README.md, I managed to finish model training following Librispeech tutorial using libri_MLP_fmllr.cfg and got the result: %WER 9.54 [ 5018 / 52576, 558 ins, 643 del, 3817 sub ] /pytorch-kaldi/repo/exp_torch/libri_MLP_fmllr_GPU_ c75_batch256/decode_test_clean_out_dnn1/wer_13_0.0, I’d like to move the trained model exp_files/final_architecture1.pkl to one of our hardware recognition system for live test. Since our existing system loads final.mdl in Kaldi format, does anyone can give any idea for converting final_architecture1.pkl to Kaldi format? Thanks in advance :-D — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#255>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEA2ZVX7RSXB5XM4IJ3XGK3T2YJYLANCNFSM5BL4QHRA .

Answer 3 · 2021-08-02T12:26:40.000Z

Unfortunately this is not possible..

…

On Mon, Aug 2, 2021, 1:22 AM spacecd ***@***.***> wrote: Thanks Mirco for the reply. I’ve heard the name of SpeechBrain in the community, and will start follow it :-D A quick question, is it possible that we convert the ASR model trained by SpeechBrain to Kaldi format? I ask this because our existing hardware recognition system is running C optimized kaldi decoder. Hi, we aren't supporting pytorch-kaldi anymore because we now haveca much better toolkit called speechbrain. My suggestion is to switch to it. … <#m_-4930076304115183559_> On Sun, Aug 1, 2021, 11:59 PM spacecd *@*.***> wrote: Hi Sir, Thanks for the detailed README.md, I managed to finish model training following Librispeech tutorial using libri_MLP_fmllr.cfg and got the result: %WER 9.54 [ 5018 / 52576, 558 ins, 643 del, 3817 sub ] /pytorch-kaldi/repo/exp_torch/libri_MLP_fmllr_GPU_ c75_batch256/decode_test_clean_out_dnn1/wer_13_0.0, I’d like to move the trained model exp_files/final_architecture1.pkl to one of our hardware recognition system for live test. Since our existing system loads final.mdl in Kaldi format, does anyone can give any idea for converting final_architecture1.pkl to Kaldi format? Thanks in advance :-D — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#255 <#255>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEA2ZVX7RSXB5XM4IJ3XGK3T2YJYLANCNFSM5BL4QHRA . — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#255 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AEA2ZVWYWQDWLNCXWMCHYPLT2YTQLANCNFSM5BL4QHRA> .

Answer 4 · 2021-08-03T07:14:39.000Z

Thanks Micro for your kindly help