 Jong Wook Kim
|
12e1089462
use stdout for printing transcription progress (#867)
|
2 年之前 |
 Markus Hennerbichler
|
ea1c266709
Fix bug where mm is mistakenly replaced with hmm in e.g. 20mm (#659)
|
2 年之前 |
 Jong Wook Kim
|
8135a7c31c
verbose outputs from pytest
|
2 年之前 |
|
Jong Wook Kim
|
9d646db9d8
print '?' if a letter can't be encoded using the system default encoding (#859)
|
2 年之前 |
|
Jong Wook Kim
|
37a4f1be6d
Release 20230117
|
2 年之前 |
 Romain Beaumont
|
b9f9b433ae
Add github action to automatically push to pypi on Release x.y.z commit (#681)
|
2 年之前 |
 Umar Farooqi
|
f0083e7eb2
Use ndimage.median_filter instead of signal.medfilter (#812)
|
2 年之前 |
|
Jong Wook Kim
|
a84191faae
rename GitHub workflow
|
2 年之前 |
|
Jong Wook Kim
|
b1d213c0c7
allow test_transcribe to run on CPU when CUDA is not available
|
2 年之前 |
|
Jong Wook Kim
|
493dfffa37
add github action to run pytest
|
2 年之前 |
 Mikko Vedru
|
0f39c89d92
Update README.md (#804)
|
2 年之前 |
|
Markus Hennerbichler
|
6df3ea1fb5
Support batch-dimension in log_mel_spectogram (#839)
|
2 年之前 |
 adamreis
|
70861c7ce3
Fix tiny transcribe() docstring typo (#857)
|
2 年之前 |
|
Jong Wook Kim
|
f82bc59f5e
torch.concatenate -> torch.cat for compatibility
|
2 年之前 |
|
Jong Wook Kim
|
28769fcfe5
word-level timestamps in Multilingual_ASR notebook
|
2 年之前 |
|
Jong Wook Kim
|
53807677fe
MultiHeadAttention to return qk as well
|
2 年之前 |
|
Jong Wook Kim
|
9323b2526c
Revert "saving the qk matrix in the attention module for convenience"
|
2 年之前 |
|
Jong Wook Kim
|
68e44bd83c
saving the qk matrix in the attention module for convenience
|
2 年之前 |
|
Jong Wook Kim
|
0b5dcfdef7
large-v2 figure and arxiv url update
|
2 年之前 |
 altryne
|
b9265e5796
Update Hebrew language code to he per IANA registry (#401)
|
2 年之前 |
 Paul Harter
|
fd8f80c8b8
Explicitly closing model file after reading it (#630)
|
2 年之前 |
|
Jong Wook Kim
|
4179ed2475
add large-v2 model
|
2 年之前 |
 jumon
|
ec1b34bb90
fix compression ratio function (#561)
|
2 年之前 |
|
Jong Wook Kim
|
eff383b27b
invoking __call__ instead of forward()
|
3 年之前 |
|
Jong Wook Kim
|
02aa851a49
fix to return only the text token ids
|
3 年之前 |
|
jumon
|
76148a56c5
suppress generating non-timestamp tokens at the beginning (#532)
|
3 年之前 |
 Vicki Anand
|
9f70a352f9
Fix attention caching to make it actually work (#370)
|
3 年之前 |
 Sumana Harihareswara
|
7f3e408e09
Add package metadata to setup.py (#315)
|
3 年之前 |
 Michael Monashev
|
f680570016
Fix bug (#305)
|
3 年之前 |
|
Jong Wook Kim
|
d18e9ea5dd
transcribe() on English-only model won't complain when language="en" is not given
|
3 年之前 |
