jimbozhang

Speech recognition/synthesis.

Xiaomi CorporationBeijing

Pinned Repositories

fixed-size-priority-queue
A priority queue with fixed size, based on STL. When the maximum size was reached, the element with the lowest priority would be removed automatically.
Language:C++4 2 02
gradio-chatgpt
A simple web-based interface for ChatGPT.
Language:Python11 1 02
hf_transformers_custom_model_ced
🤗 Transformers custom models (CED)
Language:Python2 1 20
hf_transformers_custom_model_dasheng
🤗 Transformers custom models (Dasheng)
Language:Python1 1 00
kaldi-gop
Kaldi-based goodness of pronunciation (GOP)
Language:C++139 16 3341
speechocean762
A non-native English corpus for pronunciation scoring task
103 7 721
TushouCNN
A tensorflow-compatible，dependency-free lightweight C++ library for neural network inference.
Language:C++3 1 11
xares
X-ARES：eXtensive Audio Representation and Evaluation Suite
Language:Python1 2 00
xares-template
Template for creating audio encoders compatible with X-ARES
1 1 00
yesno-example-for-undergraduates
Language:Jupyter Notebook24 3 11

jimbozhang's Repositories

jimbozhang/kaldi-gop
Kaldi-based goodness of pronunciation (GOP)
Language:C++139 16 3341
jimbozhang/speechocean762
A non-native English corpus for pronunciation scoring task
103 7 721
jimbozhang/yesno-example-for-undergraduates
Language:Jupyter Notebook24 3 11
jimbozhang/gradio-chatgpt
A simple web-based interface for ChatGPT.
Language:Python11 1 02
jimbozhang/fixed-size-priority-queue
A priority queue with fixed size, based on STL. When the maximum size was reached, the element with the lowest priority would be removed automatically.
Language:C++4 2 02
jimbozhang/hf_transformers_custom_model_ced
🤗 Transformers custom models (CED)
Language:Python2 1 20
jimbozhang/GigaSpeech
Large, modern dataset for speech recognition
Language:Shell1 1 00
jimbozhang/handle-solver
A solver for 汉兜 (Chinese idiom Wordle) puzzles
Language:Jupyter Notebook1 1 00
jimbozhang/hf_transformers_custom_model_dasheng
🤗 Transformers custom models (Dasheng)
Language:Python1 1 00
jimbozhang/k2
FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar
Language:Cuda1 1 01
jimbozhang/k2_librispeech
An example of preparing L and G FST for k2.
Language:Shell1 1 00
jimbozhang/lhotse
Language:Python1 3 21
jimbozhang/snowfall
Language:Python1 1 00
jimbozhang/xares
X-ARES：eXtensive Audio Representation and Evaluation Suite
Language:Python1 2 00
jimbozhang/xares-template
Template for creating audio encoders compatible with X-ARES
1 1 00
jimbozhang/PySpeechColab
A library of speech gadgets.
Language:Python0 1 00
jimbozhang/aes-encrypt-decrypt
Language:Python2 0
jimbozhang/busygpu
Language:Python2 0
jimbozhang/Dasheng
Source for the Interspeech 2024 Paper "Scaling up masked audio encoder learning for general audio classification"
Language:Python0 0
jimbozhang/HEAR2021_EfficientLatent
Submission to the HEAR2021 Challenge
Language:Python1 0
jimbozhang/HEAR_CED
Hear evaluation for CED models.
Language:Python0 0
jimbozhang/icefall
Language:Python1 0
jimbozhang/kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
Language:Shell1 01
jimbozhang/nbterm
Jupyter Notebooks in the terminal.
Language:Python0 0
jimbozhang/openslr
Repository for the web pages and scripts associated with OpenSLR: the open speech and language repository
Language:HTML1 0
jimbozhang/PSL
Source code for ICASSP2022 "Pseudo Strong labels for large scale weakly supervised audio tagging"
Language:Python1 0
jimbozhang/refactored-fortnight
Language:Jupyter Notebook2 0
jimbozhang/SAT
Streaming Audiotransformers for online Audio tagging
Language:Python0 0
jimbozhang/transformers-ced
Language:Python0 0
jimbozhang/WeixinBot
网页版微信API，包含终端版微信及微信机器人
Language:Python0 0