Add ROCm_whisper.md (Docker + native install guide) and docker/Dockerfile.rocm
based on rocm/pytorch:rocm7.2.4 (PyTorch 2.10.0) that installs the official
CTranslate2 v4.8.0 ROCm wheel. The default faster_whisper backend runs on AMD
GPUs out of the box with no code changes.
Tested on Radeon AI PRO R9700 (gfx1201) and Ryzen AI Max+ 395 / Radeon 8060S
(gfx1151) with ROCm 7.2.4.
Addresses #520.
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>
- Enumerate each ignored param individually in log message
- Add warnings for 'include' param (was previously silent)
- Added 6 unit tests for REST API param validation
- New params: max_retries (default 0), retry_delay (default 5s)
- On unexpected close, retries up to max_retries times
- Does not retry on server_error (server rejected connection)
- Extracted _create_websocket() helper for reuse
- Added 4 unit tests for reconnect behavior
MagicMock auto-attributes are not JSON serializable. Set language,
language_probability, and duration explicitly. Also exclude metadata
events from segment count assertion.
- stream=true now returns text/event-stream with per-segment SSE events
- Each segment yields 'data: {json}' followed by 'data: [DONE]'
- Error events streamed as 'data: {"error": ...}'
- Temp files cleaned up in finally block
- 5 new tests in test_server_extended.py (183 total passing)
Add a minimal, non-breaking hook to WhisperLive that allows external
projects to post-process transcription segments before they are sent
to the client.
Changes:
- ServeClientBase: add segment_post_processor attribute (default None)
- ServeClientBase.send_transcription_to_client: apply post_processor
per-segment with error handling (falls back to original segment)
- TranscriptionServer: add segment_post_processor parameter to run()
and wire it to each client on creation
This enables downstream projects to plug in custom processing
(e.g. formatting, PII redaction, diarization tagging) without
modifying WhisperLive core code.
- New word_timestamps option (default False) in client handshake
- When enabled, each segment includes 'words' array with per-word
start/end times and probability scores
- Wired through entire pipeline: client → server → backend → transcribe()
- Words include timestamp_offset for accurate absolute times
- REST API already supported word timestamps; now WebSocket does too
- Added 9 unit tests for word timestamp extraction and formatting
- New whisper_live/diarization.py: SpeakerDiarizer with online clustering
- Uses pyannote.audio speaker embeddings (optional dependency)
- Cosine similarity threshold for speaker matching (default 0.55)
- Running average embedding update for speaker stability
- Configurable max_speakers limit (default 10)
- Client options: enable_diarization, max_speakers
- Segments include 'speaker' field when diarization is active
- Graceful fallback: logs warning if pyannote not installed
- Added 12 unit tests (mock-based, no GPU required)
cjones
Vineet Suryan