89466f7b77
Fix NoneType crash in _process_single when VAD filters all audio
...
When VAD removes all speech from an audio chunk, transcriber.transcribe() returns (None, info). Calling list(None) raises TypeError. The _process_multi path already handles this case; this aligns _process_single to match.
2026-03-11 16:48:23 +00:00
3508b39584
Fix missing batch_config init causing CI test hang
2026-03-09 11:42:15 +00:00
e8bd4fd532
Add cross-client GPU batch inference for faster_whisper backend
2026-02-26 00:00:51 +00:00
e48d16f923
Merge pull request #398 from AlexStansfield/feature/faster-whisper-1.2.0
...
feat: update to support faster whisper 1.2.0
2026-02-11 17:57:05 +05:30
5e33aa2a7e
Enable timestamps for transcripted text
...
Add `--enable-timestamps` option to `run_client.py`
script to print out transcripted text with timestamps.
Sample output with translation enabled:
```
[0.000 -> 7.440] And so, my fellow Americans, ask not what your country can do for you.
[7.440 -> 10.300] Ask what you can do for your country.
TRANSLATION to fr:
[0.000 -> 7.440] Et donc, mes camarades américains, ne demandez pas ce que votre pays peut faire pour vous.
[7.440 -> 10.300] Demandez ce que vous pouvez faire pour votre pays.
```
Signed-off-by: Jeny Sadadia <jeny.sadadia@collabora.com >
2026-02-10 15:43:20 +05:30
29ee640409
api: add support OpenAI REST transcription api
2026-02-05 22:31:59 -05:00
f5256fc62f
feat: support HuggingFace model IDs for faster_whisper_custom_model_path
...
Previously, the server only accepted local file paths for custom Faster Whisper
models. This change allows passing HuggingFace repo IDs which are automatically
downloaded and converted to CTranslate2 format by the backend if not already in
CTranslate2 format.
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2026-01-13 16:34:04 +05:30
c43eb1dd5a
update to support faster whisper 1.2.0
2025-10-07 14:20:20 +00:00
04db67170b
ServeClientTranslation import only when enable_tranlsation is True
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-07-22 15:47:06 +00:00
2b8b245fa8
Add translation backend
...
Translate from any language to any language with alirezamsh/small100
running in a thread and reading from a queue shared with transcription thread.
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-07-22 08:54:10 +00:00
8d6ddd4f7b
Change max_clients max_connection_time from server only
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-07-21 22:52:24 +05:30
40edd25468
remove commented code
2025-07-12 22:29:30 +05:30
e597c876cf
changes to run when audio playback is muted
2025-07-07 13:21:20 +05:30
9954548075
issue 371
...
model name is of form namespace/repo_name and not os path.
2025-07-06 16:10:49 +05:30
74abf66d48
Make cache path configurable to save auto converted ct2 models
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-06-01 09:04:22 +00:00
bff88ed3e7
Auto convert hf custom whisper to ct2(faster-whisper)
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-05-29 09:23:32 +00:00
4b46371dac
Bump version v0.7.1
2025-05-15 10:25:17 +05:30
1f4c918d01
Merge pull request #376 from xXLosKrachosXx/main
...
Add transcription callback parameter to TranscriptionClient #361
2025-05-15 10:08:59 +05:30
cd327bab50
Bump version to v0.7.0
2025-05-15 09:47:44 +05:30
b91b3664c2
Add transcription callback parameter to TranscriptionClient #361
2025-05-14 23:03:14 +02:00
4ba576fb06
Merge pull request #374 from xXLosKrachosXx/main
...
Add transcription callback to Client for handling transcription results
2025-05-14 20:19:25 +05:30
188b21f1d0
Add transcription callback to Client for handling transcription results
2025-05-12 20:56:04 +02:00
d29993048d
Fix: Enable support for WebSocket streaming in client.
...
Added the `use_wss` parameter to allow the client to handle WebSocket-based streaming. This enhances flexibility for real-time transcription scenarios.
2025-05-12 16:42:11 +09:00
41d9f683a8
Add: support for secure WebSocket (WSS) connections
...
Introduce an optional `use_wss` flag to enable secure WebSocket protocol. Updated socket URL generation to dynamically select between `ws` or `wss` based on the flag value. Ensures greater flexibility when connecting to secure servers.
2025-05-12 13:53:41 +09:00
275ed4e45b
Merge branch 'main' into configure-more-params
2025-05-02 12:23:45 +02:00
7fb2d356f9
Merge pull request #368 from makaveli10/upgrade_trt_v0_18
...
Upgrade tensorrt_llm to v0.18.2
2025-04-30 12:19:39 +05:30
a2271806c3
feat: client sends new parameters to server
2025-04-28 17:21:33 +02:00
0abf8693ef
refactor: include additional parameters
...
Refactor ServeClientBase and its subclasses to include additional parameters for segment handling and audio clipping.
2025-04-25 13:09:44 +02:00
444a1df740
Resolve daemon warnings for threading methods
...
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com >
2025-04-25 00:30:08 -07:00
47ee035f65
Upgrade tensorrt_llm to v0.18.2
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-04-22 12:33:03 +00:00
9b364f267a
Remove blank segment feature
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-04-17 08:29:14 +00:00
fb3deb2745
Remove clip_audio from faster_whisper backend
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-04-15 08:00:46 +00:00
a62495b090
Integrate OpenVINO backend
...
Signed-off-by: makaveli <vineet.suryan@collabora.com >
2025-03-31 12:57:19 +05:30
c1ac71ada0
Refactor 🔨
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-03-24 16:48:33 +05:30
f5bea0a693
Bump version v0.6.3
2025-02-26 19:41:56 +05:30
379bd146fc
Bump version v0.6.2
2025-02-07 17:07:13 +05:30
87520498e9
Add option to mute audio playback for file input
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-02-05 20:23:41 +05:30
5aa5826f36
Replace ffmpeg with av lib for resampling, rtsp & hls streams
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-01-22 05:11:04 -05:00
4baccf75a7
Bump version v0.6.1
2025-01-16 10:43:26 +05:30
5e4589cfe1
Upgrade silero vad v5.0
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-01-13 11:37:58 +00:00
b6b73730fb
Fix: typo
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-01-13 11:35:22 +00:00
182b5cbd6d
Fix skipped audio chunk by recording the time of the first repition of a segment
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-01-08 13:58:34 +00:00
32ba924d8c
Bump version v0.6.0
2025-01-07 18:10:03 +05:30
c936e5f727
Add lock to thread shared variables updates/reads
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2025-01-06 06:34:02 +00:00
19c05c8231
Merge pull request #301 from makaveli10/upgrade_tensorrt
...
Upgrade tensorrt_llm==0.15.0.
2024-12-03 10:04:14 -05:00
49e232bc4d
Set segment.completed to False by default
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2024-12-03 20:09:41 +05:30
53c31f3570
Merge pull request #297 from makaveli10/support_hf_models
...
Support loading hf models.
2024-11-27 13:54:03 -05:00
7f0c7a6791
Upgrade faster_whisper==1.1.0 official release
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2024-11-26 21:36:28 +05:30
2eff360b9e
Support loading hf models
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2024-11-26 11:14:18 +05:30
c25a036c02
Upgrade tensorrt_llm to 0.15.0
...
Signed-off-by: makaveli10 <vineet.suryan@collabora.com >
2024-11-21 06:13:00 +00:00
ianwh02