Issues
- 0
[CONTRIBUTION] Speech Dataset Generator
#66 opened by davidmartinrius - 6
- 0
Can this model convert Chinese audio to text?
#58 opened by gaowenxin95 - 1
- 9
torch type mismatch error
#37 opened by pkyoung - 2
TIMIT PER
#57 opened by ankitapasad - 0
Make Requires Cuda
#56 opened by goldblum - 3
Error in seq2seq.py of Method collate
#44 opened by lypenghao - 0
Could you share your WER on librispeech?
#54 opened by iamxiaoyubei - 0
Sample generation
#45 opened by mdhasanai - 1
- 0
Loss is decrease but SER is increase
#51 opened by liangzhenlin123 - 0
Multi Gpu Training support
#50 opened by rajeevbaalwan - 1
Out of memory Error
#49 opened by tanishg98 - 0
- 1
请问有成功训练出中文汉语模型的么
#47 opened by 873765272 - 1
Make error
#46 opened by xfdywy - 2
Errors with Installation
#34 opened by Energyquantum - 4
- 0
your paper link
#43 opened by eeric - 1
- 0
Word Level LM at Line 96
#40 opened by kmohanku - 0
Pytest FAILURES
#39 opened by my-yy - 1
Librispeech
#36 opened by arattari - 0
ctc decoder with language model
#38 opened by edchengg - 3
- 1
How to get the text for a given audio file?
#31 opened by GabrielLin - 1
- 5
KeyError: 'start_and_end'
#28 opened by sroca8 - 1
- 3
pytest failure
#29 opened by JeremyCCHsu - 5
RNN Transducer training problem
#27 opened by HawkAaron - 5
transducer
#21 opened by BestSonny - 1
RNN Transducer inference problem
#26 opened by HawkAaron - 1
High quality samples?
#25 opened by claytonblythe - 1
No module named functions.ctc
#23 opened by sroca8 - 2
Results on LibriSpeech very bad
#16 opened - 1
Can't find editdistance frm
#19 opened by xavigiro - 1
transducer results
#20 opened by BestSonny - 1
- 1
make errors
#17 opened by Mitchell1314 - 1
- 0
- 1
2 errors in ctc_test.py
#13 opened by fs94007 - 1
- 1
Add licence
#12 opened by smolendawid - 2
Attention explanation
#11 opened by smolendawid - 1
- 1
- 1