Spaces:
Sleeping
Sleeping
| title: Voice Prompt v2 | |
| emoji: 🏃 | |
| colorFrom: yellow | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.42.0 | |
| app_file: app.py | |
| pinned: false | |
| license: cc | |
| short_description: Email_Writer | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |
| # 🎤 Chinese Voice → English Text Translator | |
| A Hugging Face Space powered by **OpenAI Whisper** and **MarianMT** that lets you: | |
| 1. Speak Chinese directly (🎙️ microphone input). | |
| 2. Upload an audio file in Chinese (`.wav`, `.mp3`, etc). | |
| 3. Get instant **Chinese transcription** and **English translation**. | |
| --- | |
| ## 🚀 Demo | |
| - 🎙️ Click the microphone to record your voice in Chinese. | |
| - 📂 Or upload a pre-recorded audio file. | |
| - 🈶 The app transcribes your speech into **Chinese text**. | |
| - 🌍 The app then translates that text into **English**. | |
| --- | |
| ## 🛠️ Tech Stack | |
| - [Gradio](https://gradio.app/) → User interface. | |
| - [OpenAI Whisper](https://github.com/openai/whisper) → Chinese speech-to-text. | |
| - [Helsinki-NLP/opus-mt-zh-en](https://huggingface.co/Helsinki-NLP/opus-mt-zh-en) → Chinese → English translation. | |
| - [PyTorch](https://pytorch.org/) → Deep learning backend. | |
| --- | |
| ## 📂 Files | |
| - `app.py` → Main Gradio app. | |
| - `requirements.txt` → Dependencies for Hugging Face Space. | |
| - `READM | |