Wav2Vec2 ASR Models Voice AI Tools

Fine-tuning frameworks and implementations of Wav2Vec 2.0 for automatic speech recognition across languages. Does NOT include general ASR systems using other architectures (WaveNet, etc.), TTS, or non-ASR applications of Wav2Vec.

There are 51 wav2vec2 asr models tools tracked. The highest-rated is liangstein/Chinese-speech-to-text at 48/100 with 163 stars.

Get all 51 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=voice-ai&subcategory=wav2vec2-asr-models&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	liangstein/Chinese-speech-to-text Chinese Speech To Text Using Wavenet	48	Emerging	163	Python
2	louiskirsch/speechT An opensource speech-to-text software written in tensorflow	47	Emerging	160	Python
3	Open-Speech-EkStep/vakyansh-models Open source speech to text models for Indic Languages	46	Emerging	325	—
4	oliverguhr/wav2vec2-live A live speech recognition using Facebooks wav2vec 2.0 model.	46	Emerging	378	Python
5	Open-Speech-EkStep/vakyansh-wav2vec2-experimentation Repository containing experimentation platform on how to train, infer on...	46	Emerging	88	Python
6	juliuskunze/speechless Speech-to-text based on wav2letter built for transfer learning	45	Emerging	98	Python
7	silversparro/wav2letter.pytorch A fully convolution-network for speech-to-text, built on pytorch.	45	Emerging	126	Python
8	m3hrdadfi/soxan Wav2Vec for speech recognition, classification, and audio classification	44	Emerging	273	Jupyter Notebook
9	mailong25/self-supervised-speech-recognition speech to text with self-supervised learning based on wav2vec 2.0 framework	42	Emerging	379	Python
10	bhattbhavesh91/wav2vec2-huggingface-demo Speech to Text with self-supervised learning based on wav2vec 2.0 framework...	41	Emerging	29	Jupyter Notebook
11	loretoparisi/wave2vec-recognize-docker Wave2vec 2.0 Recognize pipeline	40	Emerging	33	Python
12	HarunoriKawano/Wav2vec2.0 Implementation of the paper "wav2vec 2.0: A Framework for Self-Supervised...	39	Emerging	57	Python
13	khanld/ASR-Wav2vec-Finetune :zap: Finetune Wa2vec 2.0 For Speech Recognition	38	Emerging	149	Python
14	LearnedVector/Wav2Letter Speech Recognition model based off of FAIR research paper built using Pytorch.	36	Emerging	87	Python
15	Hamtech-ai/wav2vec2-fa fine-tune Wav2vec2. an ASR model released by Facebook	35	Emerging	36	Jupyter Notebook
16	phanxuanphucnd/wav2asr A library version of wav2vec 2.0 framework for Automatic Speech Recognition task.	34	Emerging	4	Python
17	daanzu/wav2vec2_stt_python Simple Python library, distributed via binary wheels with few direct...	33	Emerging	23	Python
18	moxeeem/ASR-pronunciation-correction Этот проект представляет систему автоматической коррекции произношения на...	32	Emerging	3	Jupyter Notebook
19	ttop32/wav2vec2-live-japanese-translator real time japanese speech recognition translator using wav2vec2	31	Emerging	39	Jupyter Notebook
20	baocin/hugging_face_example_STT_api Demonstration of Hugging Face's (https://huggingface.co/) newly released...	31	Emerging	3	Python
21	khanld/Wav2vec2-Pretraining Wav2vec 2.0 Self-Supervised Pretraining	31	Emerging	59	Python
22	oswaldoludwig/Pruning-pre-trained-models-using-evolutionary-computation This repository contains scripts to prune Wav2vec2 using a...	30	Emerging	2	Shell
23	seanghay/wav2vec2-khmer-openslr Wav2Vec2 with OpenSLR 42 (Khmer language)	30	Emerging	2	Python
24	vietai/ASR End-to-End Vietnamese Speech Recognition using wav2vec 2.0	29	Experimental	105	—
25	mpoyraz/wav2vec2-turkish Turkish Speech Recognition using Facebook's Wav2vec 2.0 models	29	Experimental	31	Python
26	KrishnaDN/BERTphone Implementation of the paper "BERTphone: Phonetically-aware Encoder...	29	Experimental	17	Python
27	HySonLab/EntityKG wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech	29	Experimental	9	Python
28	vadimkantorov/inferspeech PyTorch speech2text inference script for the NVidia openseq2seq wav2letter...	28	Experimental	10	Python
29	elerdg/ASR-for-low-resource-languages Fine-tune wav2vec2-xls-r on data from low-resource-languages	26	Experimental	6	Jupyter Notebook
30	Dhruv16S/Transcribing-Video-to-Text This repository is an implementation of the Wav2Vec2 model for converting...	25	Experimental	4	Python
31	EN10/Speech-to-Text-WaveNet Speech to Text	24	Experimental	5	Python
32	imvladikon/wav2vec2-hebrew Speech Recognition for Hebrew (using wav2vec2 models)	24	Experimental	5	Python
33	Ronnie-Leon76/Swahili-ASR This repository contains the code for fine-tuning the XLS-R Wav2Vec2 model...	23	Experimental	4	Jupyter Notebook
34	ranchlai/wav2vec-2.0 Wav2vec2 English speech recognition in PaddlePaddle	23	Experimental	4	Python
35	egorsmkv/w2v2-bert-aligner Aligner for wav2vec2-bert models	23	Experimental	3	Python
36	nicolas-dufour/self-supervised-low-res-speech This project transfert the self supervised Wav2vec2 representation to low...	23	Experimental	3	Jupyter Notebook
37	navalnica/wav2vec2-belarusian Speech to Text model for Belarusian language	22	Experimental	6	Jupyter Notebook
38	Bushramjad/XLSR-Wav2Vec2-Speech-Recognition-Urdu Speech Recognition in Urdu language by fine-tuning the pretrained...	22	Experimental	6	Jupyter Notebook
39	Narasimha1997/wavenet-stt An end-to-end speech recognition system with Wavenet. Built using C++ and python.	22	Experimental	21	Python
40	theolepage/wavlm_ssl_sv SOTA method for self-supervised speaker verification leveraging a...	20	Experimental	7	Python
41	rodrigues-aline/wav2vec2_interpretation Investigating wav2vec2 context representations and the effects of fine-tuning	20	Experimental	2	Python
42	erfanashams/w2v2viz A domain-informed probe visualiser trained on wav2vec 2.0 representations.	20	Experimental	7	Python
43	dsalnikov/wav2vec pure numpy implementation of wav2vec 2.0	19	Experimental	4	Python
44	ahammedrohit/Speech-Recognition-using-wav2vec2-with-minimum-GPU Python Colab for speech recognition with wav2vec2. Since wav2vec2 requires...	18	Experimental	2	Jupyter Notebook
45	mead-ml/audio8 Deep audio modeling	17	Experimental	1	Python
46	RaggioAI/dondza-xitsonga-asr-wav2vec2 Dondza-Xitsonga Wav2Vec2 é um modelo de Reconhecimento Automático de Fala em...	17	Experimental	6	Jupyter Notebook
47	Sreyan88/Indic-ASR Repository for pre-trained wav2vec 2.0 models on 7 Indian languages	12	Experimental	5	Python
48	Sarasadeghii/Sharif-Wav2vec2 This repo shows how to finetune the wav2vec2.0 model along with its prerequisites.	11	Experimental	3	Jupyter Notebook
49	yangarbiter/torchaudio-benchmark TorchAudio: Building Blocks for Audio and Speech Processing	11	Experimental	3	Jupyter Notebook
50	agustyawan-arif/wav2vec2-large-xlsr-53-id Performing audio transcription using the Wav2Vec2 model trained on the...	10	Experimental	2	Python
51	kahramankostas/turkce-wav2text Toplu halde verilen türkçe wav dosyalarını metin dosyasına çevirir.	10	Experimental	2	Jupyter Notebook

Comparisons in this category

wav2vec2-live and wav2vec2-live-japanese-translator (46 vs 31) self-supervised-speech-recognition and wav2vec2-huggingface-demo (42 vs 41) wav2vec2-live and wav2asr (46 vs 34) wav2letter.pytorch and Wav2Letter (45 vs 36) ASR-Wav2vec-Finetune and wav2vec2-fa (38 vs 35)