To use Language-Codec, install it using:
conda create -n xxx python=3.8
conda activate xxx
pip install -r requirements.txt
from languagecodec_encoder.utils import convert_audio
import torchaudio
import torch
from languagecodec_decoder.pretrained import Vocos
device=torch.device('cpu')
config_path = "xxx/languagecodec/configs/languagecodec.yaml"
model_path = "xxx/xxx.ckpt"
audio_outpath = "xxx"
languagecodec = Vocos.from_pretrained0802(config_path, model_path)
languagecodec = languagecodec.to(device)
wav, sr = torchaudio.load(audio_path)
wav = convert_audio(wav, sr, 24000, 1)
bandwidth_id = torch.tensor([0])
wav=wav.to(device)
features,discrete_code= languagecodec.encode_infer(wav, bandwidth_id=bandwidth_id)
audio_out = languagecodec.decode(features, bandwidth_id=bandwidth_id)
torchaudio.save(audio_outpath, audio_out, sample_rate=24000, encoding='PCM_S', bits_per_sample=16)
from languagecodec_encoder.utils import convert_audio
import torchaudio
import torch
from languagecodec_decoder.pretrained import Vocos
device=torch.device('cpu')
config_path = "xxx/languagecodec/configs/languagecodec.yaml"
model_path = "xxx/xxx.ckpt"
languagecodec = Vocos.from_pretrained0802(config_path, model_path)
languagecodec = languagecodec.to(device)
wav, sr = torchaudio.load(audio_path)
wav = convert_audio(wav, sr, 24000, 1)
bandwidth_id = torch.tensor([0])
wav=wav.to(device)
_,discrete_code= languagecodec.encode_infer(wav, bandwidth_id=bandwidth_id)
print(discrete_code)
# audio_tokens [n_q,1,t]/[n_q,t]
features = languagecodec.codes_to_features(audio_tokens)
bandwidth_id = torch.tensor([0])
audio_out = languagecodec.decode(features, bandwidth_id=bandwidth_id)
Model Name | Dataset | Training Iterations |
---|---|---|
languagecodec_paper_8nq | 5W Hours | 2.0 M |
# Process the data into a form similar to xxx/languagecodec/data/libritts_testother.txt
# xxx/languagecodec/configs/languagecodec_mm.yaml
# Modify the values of parameters such as batch_size, filelist_path, save_dir, device
Refer to Pytorch Lightning documentation for details about customizing the training pipeline.
cd xxx/languagecodec
python train.py fit --config xxx/languagecodec/configs/languagecodec_mm.yaml
If this code contributes to your research, please cite our work:
@misc{ji2024languagecodec,
title={Language-Codec: Reducing the Gaps Between Discrete Codec Representation and Speech Language Models},
author={Shengpeng Ji and Minghui Fang and Ziyue Jiang and Rongjie Huang and Jialung Zuo and Shulei Wang and Zhou Zhao},
year={2024},
eprint={2402.12208},
archivePrefix={arXiv},
primaryClass={eess.AS}
}
The code in this repository is released under the MIT license as found in the LICENSE file.