v1.4.1

Changed

• Upgraded torch to v1.13.1

What's Changed

• Upgrade torch to v1.13.1, fixes #206 by @ahmetoner in #212

Full Changelog: v1.4.0...v1.4.1

v1.4.0

Changed

• Upgraded
  • SYSTRAN/faster-whisper to v1.0.1
  • fastapi to v0.110.1
  • uvicorn to v0.29.0
  • gunicorn to v21.2.0
  • tqdm to v4.66.2
  • python-multipart to v0.0.9
  • llvmlite to v0.42.0
  • numba to v0.59.1

What's Changed

• Upgrade dependencies by @ahmetoner in #210

Full Changelog: v1.3.0...v1.4.0

v1.3.0

Added

• Compiled and added FFmpeg without LGPL libraries for license compliance

What's Changed

• Add image EXPOSE commands by @nick-allen in #188
• updated docs/endpoints.md with list of request params and example curl request by @ariym in #185
• Fix fileName with non-ASCII char error : https://github.com/ahmetone… by @zj1123581321 in #184
• Add FFmpeg compiling Docker stage by @ahmetoner in #194

Full Changelog: v1.2.4...v1.3.0

v1.2.4

Changed

• Upgraded
  • openai/whisper to v20231117
  • SYSTRAN/faster-whisper to v0.10.0

Full Changelog: v1.2.3...v1.2.4

v1.2.3

What's Changed

• Upgrade Whisper to v20231106 for large-v3 by @ahmetoner in #160

Full Changelog: v1.2.2...v1.2.3

v1.2.2

Fixed

• Fixed swagger-ui rendering issues by upgrading to v5.9.1, fixes #153 and #154

---

Full Changelog: v1.2.1...v1.2.2

v1.2.1

Enabled

• Enabled vad_filter for faster-whisper engine

Changed

• Changed misspelling in "Word level timestamps"
• Removed unused unidecode dependency
• Upgraded
  • uvicorn to v0.23.2
  • gunicorn to v21.0.1
  • tqdm to v4.66.1
  • python-multipart to v0.0.6
  • fastapi to v0.104.1
  • llvmlite to v0.41.1
  • numba to v0.58.0

---

What's Changed

• Upgrade whisper by @ahmetoner in #136
• Release 1.2.0 by @ahmetoner in #137
• Enhance faster_whisper Engine by @EvilFreelancer in #128
• Upgrade dependencies by @ahmetoner in #151

New Contributors

• @EvilFreelancer made their first contribution in #128

Full Changelog: v1.1.1...v1.2.1

v1.2.0

Changed

• Upgraded
  • openai/whisper to v20230918
  • guillaumekln/faster-whisper to v0.9.0

Added

• Added Word-Level Timestamps option for OpenAI Whisper

Updated

• Updated model conversion method (for Faster Whisper) to use Hugging Face downloader
• Updated default model paths to ~/.cache/whisper.
  • For customization, modify the ASR_MODEL_PATH environment variable.
  • Ensure Docker volume is set for the corresponding directory to use caching.

    docker run -d -p 9000:9000 -e ASR_MODEL_PATH=/data/whisper -v ./yourlocaldir:/data/whisper onerahmet/openai-whisper-asr-webservice:latest

• Removed the triton dependency from poetry.lock to ensure the stability of the pipeline for ARM-based Docker images

v1.1.1

What's Changed

• 94 gpus that dont support float16 by @ahmetoner in #103
• Update compute type by @ahmetoner in #108
• Add word level functionality for Faster Whisper by @ahmetoner in #109

Full Changelog: v1.1.0...v1.1.1

v1.1.0

What's Changed

• Docs by @ahmetoner in #72
• Fix language code typo by @ahmetoner in #77
• Adds support for FasterWhisper by @alienware in #81
• Add an optional param to skip the encoding step by @ayancey in #82
• Faster whisper by @ahmetoner in #92

New Contributors

• @alienware made their first contribution in #81
• @ayancey made their first contribution in #82

Full Changelog: v1.0.6...v1.1.0