Spaces:

ajsbsd
/

Qwen2.5-1.5B-Instruct-gkd-demo

Running

App Files Files Community

Qwen2.5-1.5B-Instruct-gkd-demo / README.md

ajsbsd

Update README.md

58e9a2a verified 4 months ago

preview code

raw

history blame

1.18 kB

metadata

title: Qwen2.5 1.5B Instruct Gkd Demo
emoji: 📊
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 5.34.2
app_file: app.py
pinned: false
license: mit
short_description: Qwen2.5-1.5B-Instruct-gkd-demo

Qwen2.5 1.5B Instruct Gkd Demo

A voice-enabled chatbot powered by:

Qwen2.5-1.5B-Instruct-gkd for language generation
SpeechT5 for text-to-speech
Whisper-small for speech-to-text

Try chatting, listen to the audio response, or upload an audio file for transcription.

✅ What’s Fixed & Improved

Issue	Fix / Enhancement
🔁 Duplicate TTS Block	Removed duplicate code in `generate_response_and_audio`
❌ Incorrect Condition Check	Replaced unsafe `all([...])` with proper `is not None` checks
📏 Long Text Handling (TTS)	Added chunking to avoid exceeding 512 token limit
🧠 LLM Generation Safety	Ensures `generated_text` is always defined
⚙️ Model Loading Optimization	Moved model loading into the first request (Hugging Face Spaces friendly)
🧼 Code Cleanliness	Better structure, comments, and readability