Guillaume Klein
cce6b53e45
Fix incorrect attribute access
2023-03-16 10:32:36 +01:00
Guillaume Klein
2007adf0b5
Fix typing of words attribute
2023-03-15 17:49:07 +01:00
Guillaume Klein
ae9898f0d8
Include duration in AudioInfo structure
2023-03-15 15:30:29 +01:00
Guillaume Klein
c5f6b91b7d
Port utility function format_timestamp
2023-03-15 15:27:20 +01:00
Guillaume Klein
eafb2c79a3
Add more typing annotations
2023-03-15 15:22:53 +01:00
Guillaume Klein
8bd013ea99
Add word-level timestamps ( #43 )
...
* Add word-level timestamps
* Fix alignment between the segments and the lists of words
* Fix truncated words list when the replacement character is decoded
* Check for empty text_tokens
* Add usage example in the readme
* Update ctranslate2 to 3.9
* Skip empty segment
* Set typing for the new methods
2023-03-15 15:02:28 +01:00
Guillaume Klein
b41fd05948
Update python_requires to >=3.8
2023-03-10 11:15:58 +01:00
Guillaume Klein
3301dd9273
Make get_input a free function
2023-03-09 12:54:41 +01:00
Guillaume Klein
c52adaca90
Create a helper class Tokenizer
2023-03-09 12:53:49 +01:00
Guillaume Klein
f0a21ea916
Use a dict to represent intermediate segments
2023-03-09 11:53:55 +01:00
Guillaume Klein
6a84df400f
Fix all_tokens handling
...
See 38f2f4d99d
2023-03-09 10:02:25 +01:00
Guillaume Klein
4176da0d68
Rename offset to seek to match the OpenAI implementation
2023-03-09 09:58:58 +01:00
Guillaume Klein
6b16b8a69c
Pad the audio instead of the spectrogram
...
See 919a713499
2023-03-08 10:50:46 +01:00
Guillaume Klein
2646906596
Fix error in decode_audio for long audio inputs
2023-03-07 10:15:36 +01:00
Guillaume Klein
01ef12a6a0
Do not ignore last segment ending with one timestamp
...
See eab8d920ed
2023-03-07 10:05:04 +01:00
Guillaume Klein
469244a57d
Update CTranslate2 to 3.8.0
2023-03-06 16:21:48 +01:00
Guillaume Klein
4a18adc382
Load the tokenizer from the model directory if it exists
2023-03-01 15:47:16 +01:00
Guillaume Klein
873992623c
Accept the audio waveform as an input to transcribe() ( #21 )
2023-02-28 19:01:31 +01:00
Guillaume Klein
ed32002aea
Add instructions to install without git clone
2023-02-27 12:21:54 +01:00
Guillaume Klein
a4f1cc8f11
Add prefix parameter
2023-02-27 12:09:40 +01:00
Guillaume Klein
528aa3e784
Make threshold parameters optional
2023-02-27 11:32:03 +01:00
Guillaume Klein
f0add58bdc
Add typing to constructor and transcribe method
2023-02-27 11:22:02 +01:00
Guillaume Klein
b1c69927f8
Update code snippet to be consistent with the conversion example
2023-02-24 15:52:23 +01:00
Guillaume Klein
ef71be09ed
Update CTranslate2 to 3.7.0
2023-02-23 11:18:58 +01:00
Guillaume Klein
f5c0e44935
Update README.md
2023-02-22 14:59:29 +01:00
Guillaume Klein
d91365e321
Minor code simplification
2023-02-22 11:02:11 +01:00
Guillaume Klein
4b8237da1b
Strip the leading space before computing the compression ratio
2023-02-22 10:28:04 +01:00
Guillaume Klein
e47e00910a
Add length_penalty parameter and correctly compute the avg log prob
2023-02-22 10:27:38 +01:00
Guillaume Klein
f5c9f15c2c
Check that the language code is valid
2023-02-21 12:10:54 +01:00
Guillaume Klein
a98a2eeec4
Use the large model in the GPU benchmark
2023-02-17 18:51:12 +01:00
Guillaume Klein
8321fcb922
Recompute the performance numbers on GPU
2023-02-17 14:48:58 +01:00
Guillaume Klein
e2094b6474
Reduce the maximum length when the prompt is longer than 448/2
2023-02-17 14:37:24 +01:00
Guillaume Klein
5b240319ec
Update benchmark results with ctranslate2==3.6.0
2023-02-16 17:38:58 +01:00
Guillaume Klein
123d9a5704
Support English-only models
2023-02-16 17:02:40 +01:00
Guillaume Klein
cda834c8ea
Update CTranslate2 to 3.6.0
2023-02-16 17:01:19 +01:00
Guillaume Klein
0b53549902
Add whisper.cpp in benchmark table
2023-02-14 17:54:50 +01:00
Guillaume Klein
17a6d83d0e
Add some performance numbers in the README
2023-02-14 16:58:05 +01:00
Guillaume Klein
cbbe633082
Add num_workers parameter
2023-02-14 09:34:05 +01:00
Guillaume Klein
c86353d323
Add task parameter
2023-02-13 21:26:25 +01:00
Guillaume Klein
f56dfc6491
Add without_timestamps parameter
2023-02-13 21:22:05 +01:00
Guillaume Klein
5e938cba4e
Bump minimum CTranslate2 requirement to 3.5.1
2023-02-13 21:16:54 +01:00
Guillaume Klein
3dc44f7bb5
Raise a more explicit error message for English-only models
2023-02-13 18:26:45 +01:00
Guillaume Klein
47a62ab975
Update README.md
2023-02-13 17:43:22 +01:00
Guillaume Klein
90f6923be0
Update code snippet to output seconds as float
2023-02-13 16:08:31 +01:00
Guillaume Klein
269b3dfb10
Expose the device_index argument ( #5 )
2023-02-13 11:06:40 +01:00
Guillaume Klein
0bcbbfa8c2
Update README.md
2023-02-12 12:05:30 +01:00
Guillaume Klein
3e7b8109cd
Add not about GPU requirements
2023-02-12 12:04:11 +01:00
Guillaume Klein
60e667e0d2
Cleanup unused import
2023-02-12 11:44:05 +01:00
Guillaume Klein
7d1d0541c8
Add the initial_prompt parameter ( #2 )
...
* Add the initial_prompt parameter
* Add docstring
2023-02-12 11:42:21 +01:00
Guillaume Klein
23d2d64259
Update transcribe.py
2023-02-11 11:47:07 +01:00
