Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-03-30 14:28:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
139 Commits 13 Branches 12 Tags 70 MiB
Commit Graph

139 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Corentin Jemine
9e653bd0ea
Fixed CoW RuntimeError in DecodingTask.run() (#240) 2022-10-04 08:49:31 -07:00
Tom Stuart
02b74308ff
Fix timestamps and strip extraneous whitespace in WebVTT output (#219) 
* Use two-digit hours in WebVTT timestamps

Per the WebVTT specification [0]:

> A WebVTT timestamp consists of the following components, in the given
> order:
>
> 1. Optionally (required if hours is non-zero):
>   1. Two or more ASCII digits, representing the hours as a base ten
>      integer.
>   2. A U+003A COLON character (:)

YouTube won’t accept timestamps containing single-digit hours.

[0] https://www.w3.org/TR/webvtt1/#webvtt-timestamp

* Strip segment text in WebVTT output

We already do this for plain text and SubRip output, so we should do it
for WebVTT too.
 2022-10-03 14:51:07 -07:00
Jibin Mathew
0b1ba3d46e
Add model_dir to arguments (#202) 
* Add model_dir to arguments

* minor formatting change

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
 2022-09-30 14:45:51 -07:00
Caleb McQuillin
60132ade70
Use , character instead of . for SRT output. (#197) 
The SRT format uses the decimal comma character as the fractional separator rather than the decimal point character. Adjust format_timestamp and write_srt to specify the separator character.

See https://en.wikipedia.org/wiki/SubRip#:~:text=the%20fractional%20separator%20used%20is%20the%20comma%2C%20since%20the%20program%20was%20written%20in%20france.
 2022-09-29 20:44:12 -07:00
Jong Wook Kim
7cb4cc21bf allowing nonzero initial temperature 2022-09-29 18:05:12 -07:00
Jong Wook Kim
30dc5c581b pointer to the show and tell section 2022-09-29 14:57:49 -07:00
Szabolcs Pasztor
5905e503b8
Update README.md (#161) 
* Update README.md

* merging paragraphs

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-29 14:18:54 -07:00
Fabiano
0457aac342
Adds missing command for install (mac) (#90) 
* Adds missing command for install (mac)

Required for users who didn't previously have Rust installed.

* minor wording change

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-29 14:08:58 -07:00
sawadata
deafef05f3
Update audio.py (#178) 
add '-nostdin' argument
 2022-09-29 12:34:04 -07:00
Vicki Anand
2b0c2971af
Don't update duration if last timestamp is same as begin (#191) 2022-09-29 12:27:48 -07:00
Jong Wook Kim
62fe7f1009 patience definition to match the paper 2022-09-27 19:00:41 -07:00
Nick Konovalchuk
b4308c4782
fix: transcribe verbosity (#140) 2022-09-26 11:46:21 -07:00
Michael Goin
9c8183a179
Use PyTorch as logits transpose for ONNX support (#141) 2022-09-26 10:54:26 -07:00
VulumeCode
2037b65f3f
Context prompt (#128) 
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-26 05:22:33 -07:00
EliEron
fc0f40981d
Write each sentence as a separate line for the txt output (#101) 
* Write each sentence as a separate line for the txt output

Write each sentence as a separate line for the txt output

* Update utils.py

Co-authored-by: EliEron <example@example.com>
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-26 04:52:28 -07:00
VulumeCode
520796a34c
fix token suppression (#123) 2022-09-26 04:35:21 -07:00
fatih
ead77fab97
add srt subtitle export utility (#102) 
* add srt subtitle export utility

* simplifying

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-26 03:50:26 -07:00
Ashutosh Tripathi
5485428c81
arch linux ffmpeg install (#93) 2022-09-26 03:24:47 -07:00
fatih
9e7e418ff1
add progress bar for transcribe loop (#100) 
* add progress bar to transcribe loop

* improved warning message for English-only models

* add --condition_on_previous_text

* progressbar renames

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-26 03:24:13 -07:00
Jong Wook Kim
5d8d3e75a4 add --condition_on_previous_text 2022-09-25 05:16:08 -07:00
Jong Wook Kim
2d3032de01 improved warning message for English-only models 2022-09-25 02:10:36 -07:00
Jong Wook Kim
8cf36f3508 allow hyphens and single quotes between words 2022-09-23 20:11:27 +09:00
Jong Wook Kim
15ab548263 nocaptions -> nospeech to match the paper figure 2022-09-23 15:45:32 +09:00
mj-kh
61989529b7
Fix possible mistake when loading model to device (#57) 
Before this change, the model is loaded into GPU regardless of the value of "device" argument in CLI.

(e.g. whisper "test.wav" --device cpu loads into GPU anyway)
 2022-09-23 15:21:47 +09:00
Niklas K
f296bcd3fa
Avoid keeping redundant copies of model weights in memory during load (#42) 
* don't keep copies of model weights in host memory

* adding type annotation

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-23 12:57:39 +09:00
Sidney Radcliffe
a4fe05aa71
Add conda environment.yml (and fix requirements.txt) (#8) 
* fix: more-itertools name in requirements.txt

* feature: minimal environment.yml for conda

* Revert "feature: minimal environment.yml for conda"

This reverts commit 8fd7438b368b0eb5df85f667fea911f293fa5e6d.

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-23 12:30:45 +09:00
Giovanni Lanzani
957ffc77de
Add rust as a dependency (#30) 
* Add rust as a dependency

* Update README.md

Co-authored-by: Jong Wook Kim <ilikekjw@gmail.com>
 2022-09-23 12:26:38 +09:00
Ram Rachum
59f543e218
Fix exception cause in audio.py (#33) 2022-09-23 12:12:37 +09:00
hanacchi
c85eaaae29
Use UTF-8 encoding to save the txt and vtt files (#37) 
Explicitly set the text encoding to UTF-8 in order to avoid UnicodeEncodeErrors

Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
 2022-09-23 12:10:55 +09:00
EliEron
759e8d47a8
Fix output_dir argument when audio file is a path (#45) 2022-09-23 11:38:37 +09:00
Micheal Taylor
c0607e8d22
Add scoop install for windows (#48) 
Adding scoop install to setup for windows for ffmpeg
 2022-09-23 11:37:57 +09:00
Jong Wook Kim
e90b8fa7e8
Merge pull request #14 from bquast/patch-1 
make LICENSE a link instead of code-formatted text
 2022-09-22 11:51:05 +09:00
Jong Wook Kim
f83cb83a42
Merge pull request #24 from ldanilov/patch-1 
fixes the link to the model paper
 2022-09-22 11:48:57 +09:00
Lev Danilov
45fc3d43c1
fixes the link to the model paper 2022-09-21 21:25:17 -04:00
Bastiaan Quast
08a739ad79
make LICENSE a link instead of code-formatted text 2022-09-21 23:17:02 +02:00
Jong Wook Kim
49a3ffc997 add section Available models and languages 2022-09-22 05:36:25 +09:00
Jong Wook Kim
cfd6bdda21 a note on speed-accuracy tradeoffs 2022-09-22 02:58:56 +09:00
Jong Wook Kim
834f00a0ea making small model the default 2022-09-22 02:45:12 +09:00
Jong Wook Kim
6e3be77e1a initial commit 2022-09-22 01:09:43 +09:00