How to use DownFlow/ASMR-f5tts with F5-TTS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
F5-TTS (F5TTS_v1_Base) finetuned on WebASMR clips: 14,389 clips cut on utterance boundaries, 24 kHz mono, reconciled transcripts. DiT + vocoder. model_last.pt is the raw trainer checkpoint; vocab.txt matches it.
model_last.pt
vocab.txt
