Text2Speech plus Speech2Text
Description:
Voice Text solutions with Gradio UI:
- Text2Speech (TTS): facebook/fastspeech2-en-ljspeech
- Speech2Text (STT): facebook/wav2vec2-base-960h
Both use pipeline (from Huggingface) to "call" the models
Pre-trained models in their specific functions. No need for fine-tuned. Data is introduced by users
pip install -r requirements.txt` #install environment.
run python file (Voice_Text_Solutions).
🧮 Text2Speech (TTS) UI:
🧮 Speech2Text (STT) UI:
Please see docs dir for full documentation.