vlad.os/whisperx-rocm-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
517 Commits 1 Branch 0 Tags
rocm
Commit Graph

67 Commits

Author SHA1 Message Date
Barabazs
a51ae7a81a feat: add centralized logging to replace ad-hoc print statements (#1254) 
* feat: add logging utility functions

* feat: add logging setup and log level argument to CLI

* feat: integrate logging across modules
 2025-10-10 08:41:06 +02:00
Barabazs
3b1b9a8c4d refactor: rename types.py to schema.py to avoid stdlib conflict 2025-10-09 14:25:58 +02:00
3manifold
64e307cc29 chore: remove redundant variable & improve load_model function documentation (#1197) 
* Remove redundant variable

* Improve function documentation
 2025-10-09 09:32:02 +02:00
Jean Du
2d9ce44329 fix(asr): load VAD model on correct CUDA device (#835) 
fix(asr): load VAD model on correct CUDA device

Previously, the VAD sub‐model was always initialized on the default CUDA device (cuda:0), even when a higher device_index was specified. This change sets `device_vad` to `cuda:{device_index}` whenever `device == 'cuda'`, while falling back to the original `device` string for non‐CUDA cases. This ensures the VAD model is loaded on the intended GPU.


Co-authored-by: dujing <dujing@xmov.ai>
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2025-07-02 08:07:59 +02:00
Barabazs
e7712f496e refactor: update import statements to use explicit module paths across multiple files 2025-03-25 16:24:21 +01:00
jademlc
8e53866704 feat: pass hotwords argument to get_prompt (#1073) 
Co-authored-by: Jade Moillic <jade.moillic@radiofrance.com>
 2025-03-24 10:47:47 +01:00
Max Bain
5e54b872a9 Merge branch 'main' into main 2025-01-13 10:09:20 +00:00
Max Bain
6be02cccfa Update asr.py 2025-01-13 10:08:09 +00:00
Barabazs
f286e7f3de refactor: improve type hints and clean up imports 2025-01-13 10:45:50 +01:00
Barabazs
73e644559d refactor: remove namespace for consistency 2025-01-13 10:45:50 +01:00
winking324
1ec527375a fix vad_method is none 2025-01-13 13:53:35 +08:00
Max Bain
aaddb83aa5 switch from case to ifelse 2025-01-11 17:11:21 +00:00
Max Bain
c288f4812a Merge branch 'main' into silero-vad 2025-01-11 17:05:53 +00:00
justintennenbaum
a90bd1ce3f dataclasses replace method 2025-01-08 17:59:13 +01:00
3manifold
79eb8fa53d Accept alternative VAD methods. Extend to use Silero VAD. 2025-01-06 13:41:46 +01:00
Barabazs
10b05fc43f refactor: replace NamedTuple with TranscriptionOptions in FasterWhisperPipeline 2025-01-05 18:56:19 +01:00
Barabazs
9a8967f27e refactor: add type hints 2025-01-05 11:48:24 +01:00
Barabazs
0f7f9f9f83 refactor: simplify imports for better type inference 2025-01-05 11:48:24 +01:00
Roque Giordano
0fdb55d317 feat: add local_files_only option on whisperx.load_model for offline mode (#867) 
Adds the parameter local_files_only (default False for consistency) to whisperx.load_model so that the user can avoid downloading the file and return the path to the local cached file if it exists.

---------

Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2025-01-01 13:16:45 +01:00
Abhishek Sharma
51da22771f feat: add verbose output (#759) 
---------

Co-authored-by: Abhishek Sharma <abhishek@zipteams.com>
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2025-01-01 13:07:52 +01:00
Icaro Bombonato
15ad5bf7df feat: update versions for pyannote:3.3.2 and faster-whisper:1.1.0 (#936) 
* chore: bump faster-whisper to 1.1.0

* chore: bump pyannote to 3.3.2

* feat: add multilingual option in load_model function

---------

Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2024-12-31 10:41:09 +01:00
Hasan Naseer
7fdbd21fe3 feat: add support for faster-whisper 1.0.3 (#875) 
---------

Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2024-12-31 10:07:42 +01:00
moritzbrantner
3ff625c561 feat: update faster-whisper to 1.0.2 (#814) 
* Update faster-whisper to 1.0.2 to enable model distil-large-v3

* feat: add hotwords option to default_asr_options

---------

Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
 2024-12-31 09:41:22 +01:00
Max Bain
bbaa2f0d1a update kwargs 2024-02-22 15:59:14 +00:00
kossaisbai
2686f74bc9 Get rid of numeral_symbol_tokens variable in printed message 2024-01-19 22:25:21 +00:00
Full Name
6bb2f1cd48 Added Vad custom option 2024-01-01 14:56:51 +05:30
MahmoudAshraf97
71a5281bde support for large-v3 2023-11-25 12:09:00 +00:00
Douglas Trajano
bd3aa03b6f Move load_model after WhisperModel 2023-11-16 08:59:28 -03:00
kaka1909
48d651e5ea Update asr.py and make the model parameter be used 2023-11-16 15:29:24 +08:00
Jakub Kukul
14a7cab8eb Pass patience and beam_size to faster-whisper. 2023-10-14 13:51:29 +02:00
Andrew Bettke
79801167ac Fix: Allow vad options to be configurable by correctly passing down to FasterWhisperPipeline. 2023-10-05 10:06:34 -04:00
Max Bain
ffd6167b26 Merge pull request #473 from sorgfresser/fix-faster-whisper-threads 2023-09-19 16:53:34 -07:00
Simon Sorg
0ae0d49d1d add faster whisper threading 2023-09-14 11:47:51 +02:00
Remc
15451d0f1c fix: correct defaut_asr_options with new options (patch 0.8) 2023-09-04 17:08:19 +02:00
Max Bain
9647f60fca Merge branch 'main' into add-merge-chunk-size-as-argument 2023-08-29 10:05:05 -06:00
陳鈞
eb771cf56d feat: Add merge chunks chunk_size as arguments. 
Suggest from https://github.com/m-bain/whisperX/issues/200#issuecomment-1666507780
 2023-08-29 23:09:02 +08:00
awerks
ea7bb91a56 Update asr.py 2023-08-17 14:49:57 +02:00
awerks
72685d0398 Update asr.py 2023-08-16 16:15:24 +02:00
awerks
4acb5b3abc Update asr.py 2023-08-16 16:11:46 +02:00
briguetjo
225f6b4d69 fix suppress_numerals 2023-07-29 19:34:51 +02:00
briguetjo
864976af23 fix issue by resetting tokenizer 2023-07-29 18:56:33 +02:00
briguetjo
9d736dca1c add some warning if languages do not match 2023-07-29 18:20:59 +02:00
briguetjo
d87f6268d0 fix preset language 2023-07-29 18:13:36 +02:00
Max Bain
d7f1d16f19 suppress numerals change logic 2023-06-05 15:44:17 +01:00
Max Bain
74a00eecd7 suppress numerals fix 2023-06-05 15:33:04 +01:00
Max Bain
b026407fd9 Merge branch 'v3' of https://github.com/m-bain/whisperX into v3 
Conflicts:
	whisperx/asr.py
 2023-06-05 15:30:02 +01:00
Max Bain
a323cff654 --suppress_numerals option, ensures non-numerical words, for wav2vec2 alignment 2023-06-05 15:27:42 +01:00
prameshbajra
5a47f458ac Added download path parameter. 2023-05-27 11:38:54 +02:00
Simon
7c5468116f Merge branch 'm-bain:main' into transcribe_keywords 2023-05-20 16:03:40 +02:00
Simon
a1c705b3a7 fix tokenizer is None 2023-05-20 15:52:45 +02:00