feat: Migrate to faster-whisper and pyannote.audio for improved transcription, word-level timestamps, and speaker diarization, and include a Gradio certificate.

feat: Integrate WhisperX for transcription, word alignment, and speaker diarization, replacing faster-whisper and adding a Gradio certificate.

Revert to WhisperX, remove faster-whisper

Update requirements.txt

Create packages.txt

Replace WhisperX with faster-whisper

claude

added original code back

Change model loading to use "small" version for improved performance

Refactor audio processing logic; streamline imports and enhance alignment and diarization functionality

Refactor audio processing and translation pipeline; add TTS service integration and update requirements

minor changes

description update

Update README.md

Update README.md

Update README.md

Update README.md

.wavs added

lfs tacing wav

req.txt

changes

initial commit