4ebfb078c5
make no beam consistent with backtrack.
2025-01-09 23:13:11 +08:00
65b2332e13
make align a bit faster.
2025-01-09 19:33:26 +08:00
69281f3a29
support timestamps for numbers.
2025-01-09 15:23:40 +08:00
a90bd1ce3f
dataclasses replace method
2025-01-08 17:59:13 +01:00
10b05fc43f
refactor: replace NamedTuple with TranscriptionOptions in FasterWhisperPipeline
2025-01-05 18:56:19 +01:00
26d9b46888
feat: include speaker information in WriteTXT when diarizing
2025-01-05 18:21:34 +01:00
9a8967f27e
refactor: add type hints
2025-01-05 11:48:24 +01:00
0f7f9f9f83
refactor: simplify imports for better type inference
2025-01-05 11:48:24 +01:00
c60594fa3b
fix: update import statement for conjunctions module
2025-01-05 11:48:24 +01:00
1c6d9327bc
feat: use model_dir as cache_dir for wav2vec2 ( #681 )
2025-01-01 13:22:27 +01:00
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
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
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
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
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
9b9e03c4cc
feat: update Norwegian models ( #687 )
...
Updated Norwegian Bokmål and Norwegian Nynorsk models
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com >
2024-12-16 11:08:48 +01:00
19eff8e79a
feat: add new align models ( #922 )
...
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com >
2024-12-16 11:06:43 +01:00
6f3bc5b7b8
Added Romanian phoneme-based ASR model ( #791 )
...
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com >
2024-12-16 08:09:53 +01:00
a898b3ba94
Remove typo in error message
2024-12-16 08:02:42 +01:00
a9e50ef0af
move model to assets
2024-12-14 22:53:53 -06:00
a83ddbdf9b
local vad model
2024-12-14 22:16:43 -06:00
3f339f9515
Update alignment.py - remove commented-out alignment modules for hr language
2024-08-09 13:00:12 +02:00
9a9b6171e6
Update alignment.py - trying another hr alignment
2024-08-08 08:37:55 +02:00
59b4d88d1d
Update alignment.py - trying another hr alignment file
2024-08-08 08:29:11 +02:00
6f70aa6beb
Update alignment.py - added croatian (hr) language
2024-08-08 08:10:55 +02:00
912920c591
Update alignment.py - added alignment for sk and sl languages
2024-08-07 10:05:17 +02:00
bbaa2f0d1a
update kwargs
2024-02-22 15:59:14 +00:00
2686f74bc9
Get rid of numeral_symbol_tokens variable in printed message
2024-01-19 22:25:21 +00:00
59962a70be
Merge pull request #646 from santialferez/diarize-patch-1
...
Update pyannote to v3.1.1 to fix a diarization problem (and diarize.py)
2024-01-03 02:35:53 +00:00
6bb2f1cd48
Added Vad custom option
2024-01-01 14:56:51 +05:30
942c336b8f
Fixes --model_dir path
2023-12-27 14:03:54 -05:00
8ae6416594
update setup.py to install pyannote.audio==3.1.1, update diarize.py to include num_speakers; to fix Issue #592
2023-12-26 13:01:49 +01:00
5dfbfcbdc0
Adding Norwegian Bokmål and Norwegian Nynorsk
...
Adding Wav2Vec2-models for Norwegian Bokmål and Norwegian Nynorsk. The models are testet together with WhisperX, and works great. For Bokmål I have added the 1B model, even if I see fairly little difference between that and the 300M model. For Norwegian Nynorsk only a 300M exist.The quality of the Wav2Vec models are also reported here: https://arxiv.org/abs/2307.01672
2023-12-19 08:48:21 +01:00
089cd5ab21
Merge pull request #585 from kurianbenoy/ml-asr
...
Add alignment model for Malayalam
2023-12-10 17:35:14 -06:00
f865dfe710
fix typo
2023-12-04 17:38:50 +03:00
4acbdd75be
add "yue" to supported languages that was added along with Large-V3
2023-12-04 17:27:54 +03:00
71a5281bde
support for large-v3
2023-11-25 12:09:00 +00:00
20161935a1
feat: pass model to 3.1 in code
2023-11-17 11:12:16 +01:00
5756b0fb13
Update alignment.py
2023-11-17 05:21:23 +05:30
aaaa3de810
Update alignment.py
2023-11-17 05:18:19 +05:30
bd3aa03b6f
Move load_model after WhisperModel
2023-11-16 08:59:28 -03:00
f5c544ff90
Merge pull request #581 from davidmartinrius/catalan_align_model
...
Add align model for catalan language.
2023-11-16 10:54:24 +00:00
9f41c49fe5
Add align model for catalan language.
2023-11-16 11:43:36 +01:00
48d651e5ea
Update asr.py and make the model parameter be used
2023-11-16 15:29:24 +08:00
4ece2369d7
Merge pull request #556 from sorgfresser/remove-space-segment-align
...
no align based on space
2023-11-11 02:03:56 +00:00
6703d2774b
Drop ffmpeg-python dependency
2023-11-10 03:26:47 +09:00
0c7f32f55c
no align based on space
2023-11-03 19:47:00 +01:00
6936dd6991
default t
2023-11-03 18:50:15 +01:00
d4a600b568
REMOVE duplicated code
2023-10-31 18:55:50 +01:00
afd5ef1d58
FIX warnings for word options
2023-10-31 18:55:35 +01:00
