 Jong Wook Kim
|
7cb4cc21bf
allowing nonzero initial temperature
|
2 years ago |
|
Jong Wook Kim
|
30dc5c581b
pointer to the show and tell section
|
2 years ago |
 Szabolcs Pasztor
|
5905e503b8
Update README.md (#161)
|
2 years ago |
 Fabiano
|
0457aac342
Adds missing command for install (mac) (#90)
|
2 years ago |
 sawadata
|
deafef05f3
Update audio.py (#178)
|
2 years ago |
 Vicki Anand
|
2b0c2971af
Don't update duration if last timestamp is same as begin (#191)
|
2 years ago |
|
Jong Wook Kim
|
62fe7f1009
patience definition to match the paper
|
2 years ago |
 Nick Konovalchuk
|
b4308c4782
fix: transcribe verbosity (#140)
|
2 years ago |
 Michael Goin
|
9c8183a179
Use PyTorch as logits transpose for ONNX support (#141)
|
2 years ago |
 VulumeCode
|
2037b65f3f
Context prompt (#128)
|
2 years ago |
 EliEron
|
fc0f40981d
Write each sentence as a separate line for the txt output (#101)
|
2 years ago |
|
VulumeCode
|
520796a34c
fix token suppression (#123)
|
2 years ago |
 fatih
|
ead77fab97
add srt subtitle export utility (#102)
|
2 years ago |
 Ashutosh Tripathi
|
5485428c81
arch linux ffmpeg install (#93)
|
2 years ago |
|
fatih
|
9e7e418ff1
add progress bar for transcribe loop (#100)
|
2 years ago |
|
Jong Wook Kim
|
5d8d3e75a4
add --condition_on_previous_text
|
2 years ago |
|
Jong Wook Kim
|
2d3032de01
improved warning message for English-only models
|
2 years ago |
|
Jong Wook Kim
|
8cf36f3508
allow hyphens and single quotes between words
|
2 years ago |
|
Jong Wook Kim
|
15ab548263
nocaptions -> nospeech to match the paper figure
|
2 years ago |
 mj-kh
|
61989529b7
Fix possible mistake when loading model to device (#57)
|
2 years ago |
 Niklas K
|
f296bcd3fa
Avoid keeping redundant copies of model weights in memory during load (#42)
|
2 years ago |
 Sidney Radcliffe
|
a4fe05aa71
Add conda environment.yml (and fix requirements.txt) (#8)
|
2 years ago |
 Giovanni Lanzani
|
957ffc77de
Add rust as a dependency (#30)
|
2 years ago |
 Ram Rachum
|
59f543e218
Fix exception cause in audio.py (#33)
|
2 years ago |
 hanacchi
|
c85eaaae29
Use UTF-8 encoding to save the txt and vtt files (#37)
|
2 years ago |
|
EliEron
|
759e8d47a8
Fix output_dir argument when audio file is a path (#45)
|
2 years ago |
 Micheal Taylor
|
c0607e8d22
Add scoop install for windows (#48)
|
2 years ago |
|
Jong Wook Kim
|
e90b8fa7e8
Merge pull request #14 from bquast/patch-1
|
2 years ago |
|
Jong Wook Kim
|
f83cb83a42
Merge pull request #24 from ldanilov/patch-1
|
2 years ago |
 Lev Danilov
|
45fc3d43c1
fixes the link to the model paper
|
2 years ago |
