SylReg-Distill

Model Details

Model Description

• Language(s) (NLP): English

Model Sources

• Repository: Code
• Paper: arXiv:2607.04064
• Demo: Project page

How to Get Started with the Model

Use the code below to get started with the model.

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 conda-forge python=3.10 pip=24.0 setuptools=81.0.0 faiss-gpu=1.13.2 uv sox
conda activate py310
export UV_PROJECT_ENVIRONMENT=$CONDA_PREFIX
uv pip install -r requirements/requirements.txt

sh scripts/setup.sh

import re

import torch
import torchaudio
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from src.flow_matching import FlowMatchingWithBigVGan
from src.s5hubert import SylRegForSyllableDiscovery

# download pretrained models from hugging face hub
encoder = SylRegForSyllableDiscovery.from_pretrained("ryota-komatsu/SylReg-Distill", device_map="cuda", dtype="auto")
decoder = FlowMatchingWithBigVGan.from_pretrained("ryota-komatsu/SylReg-Decoder", device_map="cuda", dtype="auto")
speechlm = AutoModelForCausalLM.from_pretrained("ryota-komatsu/SylReg-LM-7B-Instruct", device_map="cuda", dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("ryota-komatsu/SylReg-LM-7B-Instruct")

# load a waveform
dataset = load_dataset("fixie-ai/llama-questions", split="test")
dataset = dataset.with_format("torch")
input_values, sr = dataset[0]["audio"]["array"].unsqueeze(0), dataset[0]["audio"]["sampling_rate"]  # (1, T), int
input_values = torchaudio.functional.resample(input_values, sr, 16000)

# encode a waveform into syllabic units
outputs = encoder(input_values.to(encoder.device))
units = outputs[0]["units"]  # [3950, 67, ..., 503]
input_len = len(units)

# speech language modeling
messages = [
    {"role": "user", "content": "".join(f"<{unit}>" for unit in units)},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
).input_ids.to(speechlm.device)

generated_ids = speechlm.generate(input_ids=input_ids, do_sample=True, temperature=0.8)[0]

units = tokenizer.decode(generated_ids)
units = torch.tensor([int(unit) for unit in re.findall(r"<(\d+)>", units)], device=decoder.device)
units = units[input_len:]

# unit-to-speech synthesis
generated_speech = decoder(units.unsqueeze(0)).waveform.cpu()  # (1, T)

torchaudio.save("input.wav", input_values, 16000)
torchaudio.save("output.wav", generated_speech, 16000)

Training Details

Training Data

LibriSpeech train-clean-100

Training Hyperparameters

• Training regime: bf16 mixed precision

Hardware

4 x A6000

Citation

BibTeX:

@article{Komatsu_SylReg_2026,
  author    = {Komatsu, Ryota and Kawakita, Kota and Okamoto, Takuma and Shinozaki, Takahiro},
  title     = {Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization},
  year      = {2026},
  volume    = {7},
  journal   = {IEEE Open Journal of Signal Processing},
  pages     = {800--808},
}