WhisperPlus v0.3.0

What's Changed

• 🚀 Add AutoLLM library for improved RAG support by @kadirnar in #54
• 🚀 Add demo notebook file by @kadirnar in #55
• 🌠 Add AutoCaption Feature by @kadirnar in #56
• [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in #59
• [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in #70
• Upgrade to latest Python version and ensure standard library usage by @kadirnar in #72
• Add speechbrain dependency by @kadirnar in #74
• 🌞 Add more parameter support for Whisper pipeline by @kadirnar in #75
• 🥇 Add hqq optimization algorithm by @kadirnar in #77
• 🏄‍♂️ Add test code and Runpod platform support by @kadirnar in #78
• 💬 Add new parameters for hqq optimization method by @kadirnar in #79

Full Changelog: v0.2.0...v0.3.0

WhisperPlus v0.2.0

What's Changed

• 🐛Update requirements.txt and MANIFEST.in by @kadirnar in #41
• 🚀Add pre-commit package to requirements.txt by @kadirnar in #42
• Fix pre commit by @kadirnar in #43
• Fix/database failissue by @akashAD98 in #44
• 🌠 Update chatbot.py filename by @kadirnar in #49
• 🚀 Add Long Text Summarization Feature by @kadirnar in #50
• 🤩 Add Text-to-Speech Pipeline by @kadirnar in #51
• 📰 Update README.md file by @kadirnar in #52
• 🆙 Update Version by @kadirnar in #53

Full Changelog: v0.1.0...v0.2.0

WhisperPlus v0.1.0

What's Changed

• Update CI workflow and package testing workflow by @kadirnar in #25
• Add speaker diarization functionality by @kadirnar in #26
• Feature/rag pipeline by @akashAD98 in #31
• 🤖 Update readme.md with RAG example by @kadirnar in #32
• [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in #35
• Feature/rag function by @akashAD98 in #36
• 🤩 Update isort version and change package version by @kadirnar in #38
• 🚑Update requirements and version number by @kadirnar in #39
• 🆙Update requirements.txt and version number by @kadirnar in #40

New Contributors

• @akashAD98 made their first contribution in #31
• @pre-commit-ci made their first contribution in #35

Full Changelog: v0.0.2...v0.1.0

WhisperPlus v0.0.2

What's Changed

• feat: 🚀 Add GitHub workflows for package testing and CI, integrate logger support in whisper.py 🤖 by @kadirnar in #15
• Update GitHub Actions workflows by @kadirnar in #16
• Add Speaker Diarization Feature with Pyannote 🗣️ by @kadirnar in #17
• Update requirements.txt and TypeError error has been fixed. by @kadirnar in #19
• Update ASR model and add batch size and return by @kadirnar in #23

Full Changelog: v0.0.1...v0.0.2

WhisperPlus v0.0.1

What's Changed

• 🚀 Initial commit by @kadirnar in #1
• 🤖 Added Whisper model and applied optimizations. by @kadirnar in #5
• ✨ feat: Add YouTube Speech-to-text demo by @kadirnar in #6
• feat: 🤖 Added Hugging Face Model Deployment with Gradio for enhanced features! by @kadirnar in #7
• feat: ⭐️Now supports all openai-whisper models! 🚀 by @kadirnar in #8
• Update WhisperPlus version and fix example URL by @kadirnar in #9
• Update better downloader and audio convertion & summarization by @cobanov in #10

New Contributors

• @kadirnar made their first contribution in #1
• @cobanov made their first contribution in #10

Full Changelog: https://github.com/kadirnar/whisper-plus/commits/v0.0.1