YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
How to run Kokoro TTS locally
Please note that this is the same 32fp file taken from
https://huggingface.co/onnx-community/Kokoro-82M-v1.0-ONNX/tree/main/onnx
Download all the files to a local directory model_dir
Load Kokoro Model
from kokoro_onnx import Kokoro
kokoro = Kokoro("kokoro-v1.0.onnx", "voices-v1.0.bin") # 32fp
Convert Phonemes to Wav File
The following will save a wave file to model_dir
Output is 16bit so that it can be easily used by TTS evaluation framework.
# Assuming phonemes are already produced
import soundfile as sf
samples, sample_rate = kokoro.create(phonemes, "af_bella", is_phonemes=True)
sf.write("phonemes_test.wav", samples, sample_rate, subtype='PCM_16')
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support