Sanyuan-Chen

RecAdam

Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.

CSS_with_Conformer

Code for the ICASSP-2021 paper: Continuous Speech Separation with Conformer.

C2C-DA

Code for the AAAI-2021 paper: C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling

CSS_with_EETransformer

Code for the ICASSP-2021 paper: Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

CSS_with_TSTransformer

Code for the INTERSPEECH-2021 paper: Ultra Fast Speech Separation Model with Teacher Student Learning.

UniSpeech

Sanyuan-Chen

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

emnlp-2020-virtual-conference-images

ESC-50

ESC-50: Dataset for Environmental Sound Classification

esim-response-selection

ESIM for Multi-turn Response Selection Task

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

libri_css

Libri-CSS: dataset and evaluation pipeline

ML_hit

Let us begin to study machine learing

namedtensor

Named Tensor implementation for Torch

pinkcom

A well-designed training framework

s3prl-1

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

Sanyuan-Chen.github.io

SpecVQGAN

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

speechmetrics

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

swift

ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 30+ MLLMs

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis