Apppublic

lenaras/Speech_Engineering

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes

App README

🗣️ Speech Engineering Showcase (TTS & STT)

This interactive Gradio demo showcases the power of open-source speech-to-text (STT) and text-to-speech (TTS) technologies using public models.

🚀 Features

—🎤 Record your voice or upload audio and get instant transcription using OpenAI Whisper
—💬 Enter any English text and generate speech using Coqui TTS
—🌍 100% open-source & powered by Hugging Face Spaces

🧠 Models Used

—STT: Whisper (base) – multilingual automatic speech recognition
—TTS: Coqui TTS (Tacotron2-DDC) – English speech synthesis

💻 Tech Stack

—Python
—Gradio
—Torch, Torchaudio
—OpenAI Whisper
—Coqui TTS

📦 Installation (for local use)

bash

pip install -r requirements.txt
python app.py

📍 Deploy on Hugging Face

1.Create a new Space with Gradio SDK.
2.Upload app.py, requirements.txt, and README.md.
3.Wait for the Space to build – done!

📜 License

MIT. You are free to modify, use, and build upon this project.