F5-TTS

by AI-ModelScope text-to-speech pytorch cc-by-nc-4.0

18.9K downloads 23 likes on ModelScope updated 2025-03-21

Model card

Download F5-TTS or E2 TTS and place under ckpts/

ckpts/
    F5TTS_v1_Base/
        model_1250000.safetensors
    F5TTS_Base/
        model_1200000.safetensors
    E2TTS_Base/
        model_1200000.safetensors

Github: https://github.com/SWivid/F5-TTS
Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Get this model

hp get AI-ModelScope/F5-TTS

The huggingpeers CLI is not released yet. Once it ships, the command above will download the model. Until then, download the weights from ModelScope.

Details

HuggingPeers ID: ID hpm-1w4s3WIwKEP
Provider: ModelScope
Revision: master
Organization: AI-ModelScope
Pipeline: text-to-speech
Library: pytorch
License: cc-by-nc-4.0
Published: 2024-10-14

Files 3

Total size: 2.2 KiB
Revision: master

Browse files & hashes →

Code

GitHub · SWivid/F5-TTS ↗

Linked from the model card — we do not mirror source repositories.

Sources

ModelScope · AI-ModelScope/F5-TTS (this) · checked recently

View on ModelScope ↗