v0.1.2

What's Changed

• fix: env issue with pinned openh264 and pydantic by @Mohamad-Hussein in #16

Full Changelog: v0.1.1...v0.1.2

v0.1.1

What's Changed

• add small change in UI by @Mohamad-Hussein in #10
• add assistants using Ollama by @Mohamad-Hussein in #11
• refactor: improved file structure by @Mohamad-Hussein in #12
• feat: add agent tools and llm functionality by @Mohamad-Hussein in #13
• windows optimizations fixes and add multimodal models query by @Mohamad-Hussein in #14
• add better gui by @Mohamad-Hussein in #15

Full Changelog: v0.1.0...v0.1.1

v0.1.0 Speech-Assistant

What's Changed

• Add GUI and refactored processes for organization by @Mohamad-Hussein in #6
• translation issue fix, quality of life improvements by @Mohamad-Hussein in #8
• add translation option by @Mohamad-Hussein in #9

Full Changelog: v0.0.1...v0.1.0

v0.0.2 Speech-Assistant

This is the terminal version of Speech-Assistant that is purely a speech dictator. The next versions will focus on using LLMs for logic, and AI tools to complete requests. A GUI will also be added for showing the programs options.

Patch:

• Automatic selection of translation instead of transcription for whisper-large-v2

v0.0.1 Speech-Assistant

This is the terminal version of Speech-Assistant that is purely a speech dictator. The next versions will focus on using LLMs for logic, and AI tools to complete requests. A GUI will also be added for showing the programs options.

What's Changed

• added windows functionality by @Mohamad-Hussein in #1
• Speed improvement on recording by @Mohamad-Hussein in #2
• support for AMD GPUs on Windows and Linux by @Mohamad-Hussein in #3
• data pipeline optimization, significant decrease in speech-to-text time and effortless usability by @Mohamad-Hussein in #4
• Update README.md by @Mohamad-Hussein in #5

New Contributors

• @Mohamad-Hussein made their first contribution in #1

Full Changelog: https://github.com/Mohamad-Hussein/speech-assistant/commits/v0.0.1