obx0x3's picture
Update README.md
1cf023e verified

A newer version of the Gradio SDK is available: 6.13.0

Upgrade
metadata
title: Conversation Response
emoji: 
colorFrom: red
colorTo: green
sdk: gradio
sdk_version: 5.38.2
app_file: app.py
pinned: false
license: mit

🧠 Dementia-Aware Conversational AI Space

This Hugging Face Space (conversation-response) is a dementia-support focused conversational model using pretrained Hugging Face pipelines for:

  • 💬 Dialog generation (DialoGPT)
  • ❤️ Emotion classification (RoBERTa)
  • 🧏 ASR (automatic speech recognition) using Whisper
  • 🗣️ TTS (text-to-speech) using SpeechT5

🚀 Features

🧠 Pre-loaded Pipelines

  • conversational: microsoft/DialoGPT-medium
  • emotion: j-hartmann/emotion-english-distilroberta-base
  • asr: openai/whisper-base
  • tts: microsoft/speecht5_tts

🔧 Endpoints

/generate → Chat and Emotion

POST /generate
{
  "message": "I feel lonely today"
}
/transcribe → Audio Transcription (Whisper)

Send audio as multipart/form-data.

/speak → Text to Speech (SpeechT5)

POST /speak

{
  "message": "You're safe with me."
}

Returns: audio/wav stream.