 Paul Harter
|
fd8f80c8b8
Explicitly closing model file after reading it (#630)
|
2 jaren geleden |
 Jong Wook Kim
|
4179ed2475
add large-v2 model
|
2 jaren geleden |
 jumon
|
ec1b34bb90
fix compression ratio function (#561)
|
2 jaren geleden |
|
Jong Wook Kim
|
eff383b27b
invoking __call__ instead of forward()
|
3 jaren geleden |
|
Jong Wook Kim
|
02aa851a49
fix to return only the text token ids
|
3 jaren geleden |
|
jumon
|
76148a56c5
suppress generating non-timestamp tokens at the beginning (#532)
|
3 jaren geleden |
 Vicki Anand
|
9f70a352f9
Fix attention caching to make it actually work (#370)
|
3 jaren geleden |
 Sumana Harihareswara
|
7f3e408e09
Add package metadata to setup.py (#315)
|
3 jaren geleden |
 Michael Monashev
|
f680570016
Fix bug (#305)
|
3 jaren geleden |
|
Jong Wook Kim
|
d18e9ea5dd
transcribe() on English-only model won't complain when language="en" is not given
|
3 jaren geleden |
 David Marx
|
82725cea9c
infer download_root from XDG_CACHE_HOME if avail (#257)
|
3 jaren geleden |
 eudoxos
|
35713c66e0
Add --threads option to transcribe (#278)
|
3 jaren geleden |
 Corentin Jemine
|
9e653bd0ea
Fixed CoW RuntimeError in DecodingTask.run() (#240)
|
3 jaren geleden |
 Tom Stuart
|
02b74308ff
Fix timestamps and strip extraneous whitespace in WebVTT output (#219)
|
3 jaren geleden |
 Jibin Mathew
|
0b1ba3d46e
Add model_dir to arguments (#202)
|
3 jaren geleden |
 Caleb McQuillin
|
60132ade70
Use , character instead of . for SRT output. (#197)
|
3 jaren geleden |
|
Jong Wook Kim
|
7cb4cc21bf
allowing nonzero initial temperature
|
3 jaren geleden |
|
Jong Wook Kim
|
30dc5c581b
pointer to the show and tell section
|
3 jaren geleden |
 Szabolcs Pasztor
|
5905e503b8
Update README.md (#161)
|
3 jaren geleden |
 Fabiano
|
0457aac342
Adds missing command for install (mac) (#90)
|
3 jaren geleden |
 sawadata
|
deafef05f3
Update audio.py (#178)
|
3 jaren geleden |
|
Vicki Anand
|
2b0c2971af
Don't update duration if last timestamp is same as begin (#191)
|
3 jaren geleden |
|
Jong Wook Kim
|
62fe7f1009
patience definition to match the paper
|
3 jaren geleden |
 Nick Konovalchuk
|
b4308c4782
fix: transcribe verbosity (#140)
|
3 jaren geleden |
 Michael Goin
|
9c8183a179
Use PyTorch as logits transpose for ONNX support (#141)
|
3 jaren geleden |
 VulumeCode
|
2037b65f3f
Context prompt (#128)
|
3 jaren geleden |
 EliEron
|
fc0f40981d
Write each sentence as a separate line for the txt output (#101)
|
3 jaren geleden |
|
VulumeCode
|
520796a34c
fix token suppression (#123)
|
3 jaren geleden |
 fatih
|
ead77fab97
add srt subtitle export utility (#102)
|
3 jaren geleden |
 Ashutosh Tripathi
|
5485428c81
arch linux ffmpeg install (#93)
|
3 jaren geleden |
