adelorenzo/talk2me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
10 Commits 6 Branches 0 Tags 82 MiB
Shell 29.8%
JavaScript 24.6%
HTML 20.4%
Python 16.6%
PowerShell 8.6%
829e8c3978
Go to file
Adolfo Delorenzo 829e8c3978 Add request queue status indicator to UI 
- Added visual queue status display showing pending and active requests
- Updates in real-time (every 500ms) to show current queue state
- Only visible when there are requests in queue or being processed
- Helps users understand system load and request processing

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-02 22:29:45 -06:00
static Add request queue status indicator to UI 2025-06-02 22:29:45 -06:00
templates Add request queue status indicator to UI 2025-06-02 22:29:45 -06:00
venv quasi-final 2025-04-05 11:50:31 -06:00
.gitignore Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
app.py Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
GPU_SUPPORT.md Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
package-lock.json Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
package.json Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
README_TYPESCRIPT.md Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
README.md quasi-final 2025-04-05 11:50:31 -06:00
requirements.txt Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
setup-script.sh quasi-final 2025-04-05 11:50:31 -06:00
tsconfig.json Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00
tts_test_output.mp3 quasi-final 2025-04-05 11:50:31 -06:00
tts-debug-script.py quasi-final 2025-04-05 11:50:31 -06:00
whisper_config.py Major improvements: TypeScript, animations, notifications, compression, GPU optimization 2025-06-02 21:18:16 -06:00

README.md

Voice Language Translator

A mobile-friendly web application that translates spoken language between multiple languages using:

  • Gemma 3 open-source LLM via Ollama for translation
  • OpenAI Whisper for speech-to-text
  • OpenAI Edge TTS for text-to-speech

Supported Languages

  • Arabic
  • Armenian
  • Azerbaijani
  • English
  • French
  • Georgian
  • Kazakh
  • Mandarin
  • Farsi
  • Portuguese
  • Russian
  • Spanish
  • Turkish
  • Uzbek

Setup Instructions

  1. Install the required Python packages:

    pip install -r requirements.txt

  2. Make sure you have Ollama installed and the Gemma 3 model loaded:

    ollama pull gemma3

  3. Ensure your OpenAI Edge TTS server is running on port 5050.

  4. Run the application:

    python app.py

  5. Open your browser and navigate to:

    http://localhost:8000

Usage

  1. Select your source language from the dropdown menu
  2. Press the microphone button and speak
  3. Press the button again to stop recording
  4. Wait for the transcription to complete
  5. Select your target language
  6. Press the "Translate" button
  7. Use the play buttons to hear the original or translated text

Technical Details

  • The app uses Flask for the web server
  • Audio is processed client-side using the MediaRecorder API
  • Whisper for speech recognition with language hints
  • Ollama provides access to the Gemma 3 model for translation
  • OpenAI Edge TTS delivers natural-sounding speech output

Mobile Support

The interface is fully responsive and designed to work well on mobile devices.