v0.8.0

What's Changed

• make setup.sh to work on macos by @adamsz-lume in #379
• Add hi transcription video; add blog post section by @makaveli10 in #381
• Auto convert hf custom whisper to ct2(faster-whisper) by @makaveli10 in #378
• Add iOS client for WhisperLive (Audio-Transcription-iOS) by @ParkMazorika in #382
• Add srt download opt browser ext by @makaveli10 in #385
• issue 371 by @klonikar in #384
• Change max_clients max_connection_time from server only by @makaveli10 in #387
• Integrate live translation by @makaveli10 in #391
• fix(run_server.py): help text for max_connection_time argument by @locnnil in #397
• feat: support HuggingFace model IDs for faster_whisper_custom_model_path by @makaveli10 in #412
• Add support for new REST API matching OpenAI transcription API by @boxerab in #414
• README.md: add instructions for running client by @JenySadadia in #415
• Enable timestamps for transcripted text by @JenySadadia in #418
• feat: update to support faster whisper 1.2.0 by @AlexStansfield in #398
• Bump openai-whisper version to 20250625 by @makaveli10 in #419
• Add cross-client GPU batch inference for faster_whisper backend by @ianwh02 in #422
• Fix NoneType crash in _process_single when VAD filters all audio by @ianwh02 in #427
• feat: make display_segments configurable in Client/TranscriptionClient by @nightcityblade in #425
• Expose version in package root and update dependencies in setup.py by @makaveli10 in #429
• Fix crash when no --files provided; use microphone input instead by @makaveli10 in #430

New Contributors

• @adamsz-lume made their first contribution in #379
• @ParkMazorika made their first contribution in #382
• @klonikar made their first contribution in #384
• @locnnil made their first contribution in #397
• @boxerab made their first contribution in #414
• @JenySadadia made their first contribution in #415
• @AlexStansfield made their first contribution in #398
• @ianwh02 made their first contribution in #422
• @nightcityblade made their first contribution in #425

Full Changelog: v0.7.1...v0.8.0

v0.7.1

What's Changed

• Integrate openvino by @makaveli10 in #348
• Fix typo in setup.py by @Perseus14 in #353
• Remove clip_audio from faster_whisper backend by @makaveli10 in #354
• Remove blank segment feature by @makaveli10 in #359
• Resolve daemon warnings for threading methods by @emmanuel-ferdman in #366
• Upgrade tensorrt_llm to v0.18.2 by @makaveli10 in #368
• Add possibility to configure more parameters by @giubots in #367
• Add: support for secure WebSocket (WSS) connections by @rover0811 in #373
• Add transcription callback to Client for handling transcription results by @xXLosKrachosXx in #374
• Update tensorrt_llm docker setup by @makaveli10 in #375
• Add transcription callback parameter to TranscriptionClient #361 by @xXLosKrachosXx in #376

Full Changelog: v0.6.3...v0.7.1

v0.6.3

What's Changed

• Fix setup.py onnxruntime version for py312 pypi installation support by @makaveli10 in #341

Full Changelog: v0.6.2...v0.6.3

v0.6.2

What's Changed

• Revert to 12.4.1 base image by @makaveli10 in #321
• Replace ffmpeg with av lib for resampling, rtsp & hls streams by @makaveli10 in #331
• Add support py 312 by @makaveli10 in #333
• Add option to mute audio playback for file input by @makaveli10 in #334

Full Changelog: v0.6.1...v0.6.2

v0.6.1

What's Changed

• Fix skipped audio chunk by @makaveli10 in #318
• Upgrade silero vad v5 by @makaveli10 in #319
• Fix package name by @makaveli10 in #320

Full Changelog: v0.6.0...v0.6.1

v0.6.0

What's Changed

• Upgrade tensorrt-llm==0.10.0 by @makaveli10 in #276
• Expose client manager args by @makaveli10 in #284
• Fix srt file missing segments by @makaveli10 in #292
• Upgrade faster-whisper 1.1.0rc0 by @makaveli10 in #296
• Upgrade faster_whisper==1.1.0 official release by @makaveli10 in #298
• Support loading hf models by @makaveli10 in #297
• Fix requirements & tests for py38 by @makaveli10 in #299
• Upgrade tensorrt_llm==0.15.0 by @makaveli10 in #301
• Set docker tesnorrt job timeout to 60 mins by @makaveli10 in #307
• Add lock to thread shared variables updates/reads by @makaveli10 in #316

Full Changelog: v0.5.1...v0.6.0

v0.5.1

What's Changed

• Backslash missing in example by @t-nil in #236
• Making backend arg safer by @berkaybilik in #243
• Pin silero VAD onnx model version to v4.0 by @makaveli10 in #247
• Fix deadlock issue in FFmpeg subprocess by ensuring stderr is consumed by @sondt2709 in #257
• Discard no speech segments by @makaveli10 in #262
• Initialize last_segment to None by @makaveli10 in #272
• Set compute_type based on device capability by @makaveli10 in #274

Full Changelog: v0.5.0...v0.5.1

v0.5.0

What's Changed

• Improve cpu and gpu Dockerfiles, resulting in much smaller images by @peldszus in #206
• Add option: save network stream to local file while transcribing by @fraic in #192
• fix: limit CPU usage for VAD onnxruntime inference session by setting… by @makaveli10 in #215
• Add support for RTSP stream by @dshepelev15 in #212
• Make writing audio frames optional by @makaveli10 in #216
• Expose the srt file location of Transcription client by @chien-liu in #224
• Update tensorrt llm to v0.9.0 by @makaveli10 in #227
• Single model mode by @peldszus in #223

Full Changelog: v0.4.1...v0.5.0

v0.4.1

What's Changed

• Don't clear server_error flag on close. by @jsichi in #187
• Fix client close by @makaveli10 in #190

Full Changelog: v0.4.0...v0.4.1

v0.4.0

What's Changed

• build & push docker image on every new tag by @makaveli10 in #161
• Upgrade faster whisper==1.0.1 by @makaveli10 in #163
• Handle failure on systems without microphones by @FlippFuzz in #173
• Fix faster whisper version in setup.py by @FlippFuzz in #175
• Add support for processing same audio stream via multiple clients running different tasks. by @jsichi in #174

New Contributors

• @FlippFuzz made their first contribution in #173
• @jsichi made their first contribution in #174

Full Changelog: v0.3.0...v0.4.0