git clone https://github.com/ryota-komatsu/speaker_disentangled_hubert.git
cd speaker_disentangled_hubert
sudo apt install git-lfs  # for UTMOS
conda create -y -n py310 -c pytorch -c nvidia -c conda-forge python=3.10.18 pip=24.0 faiss-gpu=1.11.0
conda activate py310
pip install -r requirements/requirements.txt
sh scripts/setup.sh

python

import torchaudio
from src.flow_matching import FlowMatchingWithBigVGan
from src.s5hubert import S5HubertForSyllableDiscovery
wav_path = "/path/to/wav"
# download pretrained models from hugging face hub
encoder = S5HubertForSyllableDiscovery.from_pretrained("ryota-komatsu/s5-hubert", device_map="cuda")
decoder = FlowMatchingWithBigVGan.from_pretrained("ryota-komatsu/s5-hubert-decoder", device_map="cuda")
# load a waveform
waveform, sr = torchaudio.load(wav_path)
waveform = torchaudio.functional.resample(waveform, sr, 16000)
# encode a waveform into syllabic units
outputs = encoder(waveform.to(encoder.device))
# syllabic units
units = outputs[0]["units"]  # [3950, 67, ..., 503]
units = units.unsqueeze(0)
# unit-to-speech synthesis
audio_values = decoder(units)

Training Hyperparameters

Training regime: fp16 mixed precision

ryota-komatsu/s5-hubert-decoder-ft

Model Card for Model ID

Model Details

Model Description

Model Sources

How to Get Started with the Model

Training Hyperparameters

ryota-komatsu/
s5-hubert-decoder-ft