A post dated October 21, 2024, says the E2-F5-TTS project added a Gradio app for fine-tuning the model with user-provided audio, with automatic transcription of audio clips.
On October 21, 2024, the E2-F5-TTS project announced a Gradio app for fine-tuning the model using audio supplied by the user. The app also transcribes clips automatically. The post describes an interface-based workflow for engineers to adapt a speech synthesis model to their own audio.
To verify the scope and details, consult the project's original announcement or record and check its description of the interface and automatic transcription. The note does not specify requirements, limitations, or quality results, so those details should not be assumed.