- New whisper_live/metrics.py with Counter, Gauge, Histogram metrics
- Track connections (opened/closed/rejected), transcription latency,
audio processed, segments emitted, REST requests, and errors
- All metric helpers are no-ops when prometheus_client not installed
- --metrics_port CLI flag to expose /metrics endpoint (0 = disabled)
- Metrics integrated into server.py, base.py at key instrumentation points
- 17 new tests in tests/test_metrics.py (178 total passing)
- MAX_BUFFER_DURATION_S (45): max audio buffer before trimming
- BUFFER_TRIM_DURATION_S (30): duration to discard on trim
- CLIP_THRESHOLD_DURATION_S (25): stale audio clip threshold
- CLIP_TAIL_DURATION_S (5): audio tail to keep after clipping
- All values can now be overridden by subclasses
- --translate: Whisper built-in to-English translation (task=translate)
- --enable_translation: M2M100 any-to-any translation backend
- Added warning when both flags are used simultaneously
- Updated help text to distinguish the two features
- max_clients must be >= 1
- max_connection_time must be > 0
- batch_max_size must be >= 1 (when batch enabled)
- batch_window_ms must be >= 0 (when batch enabled)
- Added 5 new tests for parameter validation
- Add MAX_TRANSCRIPT_LENGTH (500) and MAX_TRANSLATION_QUEUE_SIZE (100)
class constants to ServeClientBase
- Trim transcript and text lists after each update_segments() call
- Create translation queue with maxsize to prevent unbounded growth
- Added tests for _trim_transcript()
- All ClientManager methods (add_client, get_client, remove_client,
get_wait_time, is_server_full, is_client_timeout) now protected by
a threading.Lock
- cleanup() called outside the lock to avoid holding it during I/O
- is_server_full() computes wait time inline under lock instead of
calling get_wait_time() to avoid nested lock acquisition
- Added concurrent thread safety tests for add/remove and get operations
these new test cover issues such as thread safety, VAD thresholding,
message routing, error handling etc. that weren't covered by existing
tests. Mocking is used to avoid dependencies on GPU, ONNX etc.
- 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>
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.
Replace hardcoded [-4:] truncation with a configurable display_segments
parameter (default: 4) in both Client and TranscriptionClient classes.
Fixes#377
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>
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>
Aaron Boxer