 Jong Wook Kim
|
c09a7ae299
Update decoding.py (#1219)
|
%!s(int64=2) %!d(string=hai) anos |
 Fernando O. Gallego
|
b0022b3283
Update decoding.py (#1155)
|
%!s(int64=2) %!d(string=hai) anos |
 Arseniy Bushyn
|
76c901ab8d
Update README.md to reference tiktoken (#1105)
|
%!s(int64=2) %!d(string=hai) anos |
 ryanheise
|
43940fc978
Implement max line width and max line count, and make word highlighting optional (#1184)
|
%!s(int64=2) %!d(string=hai) anos |
|
ryanheise
|
255887f219
Squash long words at window and sentence boundaries. (#1114)
|
%!s(int64=2) %!d(string=hai) anos |
 K.B.Dharun Krishna
|
a151816b6b
python-publish.yml: bump actions version to fix node warning (#1211)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
b5851c6c40
Update tokenizer.py (#1163)
|
%!s(int64=2) %!d(string=hai) anos |
 Jong Wook Kim
|
6dea21fd7f
Release 20230314
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
79c43e4859
abort find_alignment on empty input (#1090)
|
%!s(int64=2) %!d(string=hai) anos |
 Guillaume Klein
|
5f9ac653b7
Fix truncated words list when the replacement character is decoded (#1089)
|
%!s(int64=2) %!d(string=hai) anos |
 Akash Mahajan
|
ba88b8e1b3
fix github language stats getting dominated by jupyter notebook (#1076)
|
%!s(int64=2) %!d(string=hai) anos |
|
Guillaume Klein
|
671ac5a4ce
Fix alignment between the segments and the list of words (#1087)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
839639a223
Use tiktoken (#1044)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
ad3250a846
Release 20230308
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
c4b50c0824
kwargs in decode() for convenience (#1061)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
38f2f4d99d
fix all_tokens handling that caused more repetitions and discrepancy in JSON (#1060)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
aac47c9834
fix typo
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
26807ec6d3
Release 20230307
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
919a713499
attempt to fix the repetition/hallucination issue identified in #1046 (#1052)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
38e990d853
Use triton==2.0.0 (#1053)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
924e1f8e06
Try installing triton only if linux & x86_64 (#1051)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
4b0d5e58d0
Update setup.py
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
8180fde939
Release 20230306
|
%!s(int64=2) %!d(string=hai) anos |
 Local State
|
c6e4e5efb3
remove auxiliary audio extension (#1021)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
b80bcf610d
apply formatting with `black` (#1038)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
500d0fe966
word-level timestamps in `transcribe()` (#869)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
eab8d920ed
Decoding improvements (#1033)
|
%!s(int64=2) %!d(string=hai) anos |
 Roman Vasilenko
|
3e1780fd37
Update README.md (#894)
|
%!s(int64=2) %!d(string=hai) anos |
 Andrey Chernykh
|
7858aa9c08
Fix infinite loop caused by incorrect timestamp tokens prediction (#914)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jong Wook Kim
|
5c1a8c10e7
clarify that 3.11 is not supported
|
%!s(int64=2) %!d(string=hai) anos |
