- --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.
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>
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>
Aaron Boxer