cjones/WhisperLive
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
634 Commits 2 Branches 20 Tags
a71c5785704b2053abf0c7390463d76c1160d79d
Commit Graph

73 Commits

Author SHA1 Message Date
Quang Tran a71c578570 fix: address PR review comments on StreamingTranscriptionClient 2026-07-08 22:49:23 +07:00
Quang Tran f4f1b1d8be feat: support manual audio streaming from any source 2026-07-08 22:46:34 +07:00
Aaron Boxer 2debc0ee80 Make initial_prompt and vad_parameters accessible from the client 
Expose initial_prompt and vad_parameters as flat client parameters
(consistent with hotwords, send_last_n_segments, etc.), send them as
flat handshake keys, and read them server-side with null-safe
options.get(...). Supersedes #283; avoids the options-bag None.get crash.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 11:36:26 -04:00
Vineet Suryan e4160d2d06 Merge pull request #513 from SuperCowProducts/clarify-installation-instructions 
Make install instructions clearer
 2026-06-26 16:03:33 +05:30
nightcityblade 471c3fd6b4 docs: add macOS OpenMP workaround 2026-06-24 11:14:48 -04:00
Alessandro Griseta 81ff199a70 First venv activate, then pip install 2026-06-18 12:29:43 +02:00
Aaron Boxer 44940e2834 Support known speaker hints in REST API 2026-06-14 12:17:44 -04:00
nightcityblade 32c1b18c9f fix: support uint8 websocket audio format 2026-06-04 16:04:38 -04:00
Vineet Suryan cdc661ce28 Merge pull request #434 from nightcityblade/fix/issue-405 
docs: fix setup instructions reported in #405
 2026-05-26 13:17:37 +05:30
Aaron Boxer 8bde966c1e docs: remove features from README that moved to Aavaaz 
Remove authentication, rate limiting, and auto-reconnect documentation
since these features now live in the Aavaaz project.
 2026-05-15 10:45:31 -04:00
Aaron Boxer 18de3eacc7 Document all new features in README 
- Added 'Advanced Features' section with 8 subsections
- Word-level timestamps: WebSocket JSON example
- Custom vocabulary / hotwords: usage and REST API support
- Speaker diarization: setup, pyannote dependency, output format
- Authentication: API key for REST + WebSocket
- Rate limiting: per-IP RPM configuration
- Auto-reconnect: max_retries / retry_delay
- Batch inference: CLI flags
- Raw PCM input: int16 normalization
- Updated table of contents
 2026-05-15 09:01:48 -04:00
nightcityblade 68a8b57e66 docs: fix setup instructions errors reported in #405 
- Clarify that setup.sh installs portaudio system dependency and list
  per-distro package names
- Add missing --gpus all flag to TensorRT Docker run command
- Fix Docker TensorRT example showing multiple --trt_model_path on one
  command (should be separate alternatives)
- Document --trt_py_session flag as workaround for TensorRT C++ session
  crashes (CrossAttentionMask warnings)

Closes #405

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 11:09:40 +08:00
Vineet Suryan 6c8142a9d2 Merge pull request #415 from JenySadadia/run-client-docs 
README.md: add instructions for running client
 2026-02-06 20:03:19 +05:30
Aaron Boxer 29ee640409 api: add support OpenAI REST transcription api 2026-02-05 22:31:59 -05:00
Aaron Boxer b9ae2af8e6 setup.sh: support Fedora 2026-02-05 22:31:59 -05:00
Jeny Sadadia 9251394047 README.md: add instructions for running client 
Specify command to run client script.

Signed-off-by: Jeny Sadadia <jeny.sadadia@collabora.com>
 2026-02-03 17:11:40 +05:30
makaveli10 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
makaveli10 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
바견규 f3acfa2f18 Add iOS client section to main README/ modify iOS README 2025-06-28 07:21:34 +09:00
makaveli 4ae3825661 Merge pull request #378 from makaveli10/auto_convert_faster_whisper 
Auto convert hf custom whisper to ct2(faster-whisper)
 2025-06-02 17:52:19 +05:30
makaveli10 05002d6ded Add hi transcription video; add blog post section 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2025-06-02 10:52:48 +00:00
makaveli10 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
makaveli ae169245a1 Update tensorrt_llm docker setup 
Remove tensorrt build from ci due to space limitations

Signed-off-by: makaveli <vineet.suryan@collabora.com>
 2025-05-14 20:29:13 +05:30
makaveli10 47ee035f65 Upgrade tensorrt_llm to v0.18.2 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2025-04-22 12:33:03 +00:00
makaveli a62495b090 Integrate OpenVINO backend 
Signed-off-by: makaveli <vineet.suryan@collabora.com>
 2025-03-31 12:57:19 +05:30
makaveli10 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
makaveli10 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
Marcus Edel 19c05c8231 Merge pull request #301 from makaveli10/upgrade_tensorrt 
Upgrade tensorrt_llm==0.15.0.
 2024-12-03 10:04:14 -05:00
makaveli10 2eff360b9e Support loading hf models 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-26 11:14:18 +05:30
makaveli10 c25a036c02 Upgrade tensorrt_llm to 0.15.0 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-21 06:13:00 +00:00
makaveli10 617fda2864 Update Readme 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-10-10 08:43:21 -04:00
makaveli10 a317597f01 Update README: fix typo 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-09-16 00:32:16 -04:00
Florian Meißner a8b9275013 Update README.md 2024-06-15 12:29:36 +02:00
makaveli 5b9bc2bc0e Merge pull request #223 from peldszus/single-model-mode 
Single model mode
 2024-06-07 11:10:52 +05:30
Anshul Kharb 761bb61e87 fix spelling of detection in README.md 2024-06-05 23:14:13 +05:30
Andreas Peldszus 14077315ae Fix argparser option 2024-06-05 10:34:22 +02:00
Andreas Peldszus ab17c4dbc6 Make single model mode the default, update readme 2024-06-05 09:47:52 +02:00
makaveli10 f73a146eb9 Update TensorRT backend tensorrt_llm==0.9.0 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-06-03 05:24:41 -04:00
Andreas Peldszus 1ac7a278bb Update README 2024-05-31 15:07:01 +02:00
makaveli10 399e9e7efe Fix README typo 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 11:18:35 +05:30
makaveli10 8f373c3537 Update README 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 11:06:49 +05:30
makaveli 03e30e1fed Merge pull request #212 from dshepelev15/feat/RTSP_support 
Add support for RTSP stream
 2024-05-28 10:48:13 +05:30
makaveli10 819ab35b28 fix: limit CPU usage for VAD onnxruntime inference session by setting OMP_NUM_THREADS 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-05-24 04:58:49 -04:00
dshepelev15 615c9c7aed Add support for RTSP stream 2024-05-17 17:32:09 +03:00
makaveli10 b47a56ca6d update readme to use ghcr docker containers 2024-02-21 22:50:56 +05:30
makaveli10 2e9f67ba0b Merge remote-tracking branch 'upstream/main' into vad_option 2024-02-20 11:43:56 +05:30
makaveli10 b04cffc458 update readme; remove common content 2024-02-16 17:11:56 +05:30
makaveli10 fd7c5965b3 add whisper live demo video 2024-02-16 13:28:02 +05:30
makaveli10 e3c7666cf7 update readme with use_vad 2024-02-15 18:13:26 +05:30
Sasa Trivic 17d62272cf Update README.md 
Remove multilingual from README
 2024-02-04 17:52:21 +01:00