• Stars
    star
    41
  • Rank 668,415 (Top 14 %)
  • Language
    Python
  • Created about 3 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

More Repositories

1

awesome-chatgpt-dataset

Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!
Python
688
star
2

TextRL

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
Python
537
star
3

Codec-SUPERB

Audio Codec Speech processing Universal PERformance Benchmark
Python
201
star
4

tw_stocker

keep tracking and store taiwan stock information
Python
100
star
5

TFkit

🤖📇 handling multiple nlp task in one pipeline
Python
56
star
6

vall-e-encodec

Python
41
star
7

BertGenerate

Fine tuning bert for text generation
Jupyter Notebook
38
star
8

asr-trainer

one script for xls-r/xlsr/whisper fine-tuning
Python
37
star
9

aidev

Revolutionize your development workflow with AI-powered code assistance, automating mock tests, suggestions, and unit test generation in a single Python CLI tool.
Python
35
star
10

NLPrep

🍳 NLPrep - dataset tool for many natural language processing task
Python
28
star
11

BDG

Code for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."
Python
27
star
12

Phraseg

Phraseg - 一言:新詞發現工具包
Jupyter Notebook
26
star
13

wav2vec2-xlsr-multilingual-56

56 language, 1 model Multilingual ASR
Python
23
star
14

FTA

Technical Analysis on Cryptocurrency
Python
23
star
15

ChineseErrorDataset

CGED & CSC
22
star
16

asrp

ASR text preprocessing utility
Python
20
star
17

nlp2go

🏃 hosting nlp models in one line
CSS
20
star
18

ipa2

Tools for convert Text to IPA in python
Python
16
star
19

nlp2

⚙️Tool for NLP - handle file and text
Python
15
star
20

awesome-question-answering-dataset

A list of awesome machine question answering dataset - 機器問答數據集
15
star
21

pretrain_bart

training BART from scratch
Python
12
star
22

SnapShare

Linking Your Phone To Computer Browser With Socket.io.
JavaScript
10
star
23

causal-lm-trainer

Python
8
star
24

wav2vec-u-exp

Build and Run Wav2vec Unsupervised Experiment
Dockerfile
8
star
25

whisper-live-asr-demo

run whisper on CPU/GPU server
JavaScript
8
star
26

gpu-info-api

🐱‍💻 GPU Info API is an API that provides detailed information about Nvidia, AMD, and Intel GPUs. The information is extracted from Wikipedia and stored in JSON format.
Python
8
star
27

t5lephone

phoneme byt5
Python
7
star
28

MMLM

Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra
Python
7
star
29

llm-estimator

Effortlessly predict training time, loss, and cost for LLM model training
JavaScript
6
star
30

WikiExtractor

Extract Knowledge from wiki dump file
Python
6
star
31

react-media-viewer

Ready to go Media Player Component for React.
JavaScript
6
star
32

dtokenizer

discretize everything into tokens
Python
6
star
33

hubert-cluster-code

Extract clustering feature from hubert
5
star
34

pytorch-tta

Pytorch implementation of "Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning".
Python
5
star
35

GSQA

Generative Spoken Question Answering
Python
4
star
36

taiwan-company-network

台灣公司投資關係圖
CSS
4
star
37

DevLEGO

Create your development Env like LEGO blocks, run your projects on any device - be it a PC, Web, Phone or Tablet!
Shell
4
star
38

awesome-evaluation-lm

Collection Of Automated Language Model Assessment
3
star
39

fastpages

Jupyter Notebook
3
star
40

modelhub

3
star
41

Gossiping-Chinese-Positive-Corpus

PTT 八卦版問答-正面-中文語料
3
star
42

survey-builder

survey builder for human evaluation
JavaScript
3
star
43

voidful

Python
3
star
44

audio-preprocessing-pipeline

Python
3
star
45

DG-Showcase

Showcase for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."
CSS
3
star
46

hubert-pretrain

using huggingface trainer to pre-train hubert
Python
2
star
47

dpr-multilingual

A multilingual version of DPR
2
star
48

telenotify

Python
2
star
49

tts-corpus-creator

collection of different source of TTS api for generating corpus.
Python
2
star
50

diff-aspect-set-dg

Python
2
star
51

depack

Extract files from any type of archive in command line
Python
2
star
52

Data2QA

Unified QA with different modality input
Python
2
star
53

bindtorchaudio

`bindtorchaudio` is a Python package that allows for easy installation of the `torchaudio` library, which provides audio processing functionalities for the PyTorch machine learning framework.
Python
2
star
54

seq2seq-lm-trainer

This is a simple example of using the T5 model for sequence-to-sequence tasks, leveraging Hugging Face's `Trainer` for efficient model training.
Python
2
star
55

PPA

Prompt Pool Agent
Python
2
star
56

bforce

bruteforce is all you need in a unstable system
Python
1
star
57

twcc-usage-slack-bot

TWCC GPU Usage Notification Slack Bot
Python
1
star
58

shows

lib for system monitoring with CPU/GPU/DISK/MEM/NET
Python
1
star
59

get-stat

lib for system monitoring in Python / Web API (CPU/GPU/DISK/MEM/NET/SERVICE)
1
star
60

NLPrep-Datasets

HTML
1
star
61

pearl

PEARL - Optimize Prompt Selection for Enhanced Answer Performance Using Reinforcement Learning
Python
1
star
62

uni-superb

Python
1
star
63

huggingface_notebook

Jupyter Notebook
1
star
64

superb-website

JavaScript
1
star
65

leverage-lm

small lm + RAG > LLM
1
star
66

fbcrawler

Python
1
star
67

SoundON

Python
1
star