feat: Real-time French-to-English translator for Apple Silicon #136
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
- Replace STT with LightningWhisperMLX Medium for Apple Silicon - Switch LLM to Llama-3.2-3B-Instruct-8bit MLX format - Update TTS to Melo TTS - Keep Silero VAD for voice detection Performance: - Optimize latency (~4s end-to-end) - Focus on French-to-English translation - Add video call platforms support (Teams, Zoom, FaceTime) - Test & validate on M2 chip with 22GB RAM Changes: - Modify system prompt for translation tasks - Remove CUDA components - Streamline pipeline for Apple Silicon - Add real-time processing optimizations Tested on MacBook Air M2, compatible with major video call platforms except Google Meet. Based on original speech-to-speech project, inspired by Andrés Marafioti's work.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
Performance:
Changes:
Tested on MacBook Air M2, compatible with major video call platforms except Google Meet.
Based on original speech-to-speech project, inspired by Andrés Marafioti's work.