Pinned Repositories
KeSpeech
The repo provides information about KeSpeech dataset.
FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Hpyformer
Hpyformer base FunASR
Paraformer-V2
来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition
s3prl
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Chinese-LLaMA-Alpaca-3
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
NiniAndy's Repositories
NiniAndy/Paraformer-V2
来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition
NiniAndy/Hpyformer
Hpyformer base FunASR
NiniAndy/DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
NiniAndy/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
NiniAndy/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
NiniAndy/s3prl
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
NiniAndy/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit