End-to-End ASR Frameworks Voice AI Tools

PyTorch-based implementations of complete automatic speech recognition systems with integrated acoustic modeling, feature extraction, and decoding. Does NOT include ASR evaluation metrics, language models, individual components (vocoder, G2P), or non-PyTorch frameworks like Kaldi-only solutions.

There are 109 end-to-end asr frameworks tools tracked. 7 score above 50 (established tier). The highest-rated is TensorSpeech/TensorFlowASR at 69/100 with 1,005 stars and 930 monthly downloads.

Get all 109 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=voice-ai&subcategory=end-to-end-asr-frameworks&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	TensorSpeech/TensorFlowASR :zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in...	69	Established	1,005	Python
2	xinjli/allosaurus Allosaurus is a pretrained universal phone recognizer for more than 2000 languages	65	Established	715	Python
3	dangvansam/viet-asr VietASR - Vietnamese Automatic Speech Recognition	61	Established	165	Python
4	wenet-e2e/wenet Production First and Production Ready End-to-End Speech Recognition Toolkit	57	Established	5,056	Python
5	srvk/eesen The official repository of the Eesen project	51	Established	834	C++
6	sooftware/kospeech Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition...	51	Established	638	Python
7	hirofumi0810/neural_sp End-to-end ASR/LM implementation with PyTorch	51	Established	594	Python
8	Audio-WestlakeU/VINP Official PyTorch implementation of 'VINP: Variational Bayesian Inference...	49	Emerging	31	Python
9	yl4579/AuxiliaryASR Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)	48	Emerging	125	Python
10	openspeech-team/openspeech Open-Source Toolkit for End-to-End Speech Recognition leveraging...	48	Emerging	718	Python
11	gentaiscool/end2end-asr-pytorch End-to-End Automatic Speech Recognition on PyTorch	48	Emerging	304	Python
12	clovaai/ClovaCall ClovaCall dataset and Pytorch LAS baseline code (Interspeech 2020)	48	Emerging	223	Python
13	iamjanvijay/rnnt_decoder_cuda An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.	48	Emerging	67	Cuda
14	voicekit-team/T-one T-one is a high-performance streaming ASR pipeline for Russian, specialized...	47	Emerging	249	Python
15	freewym/espresso Espresso: A Fast End-to-End Neural Speech Recognition Toolkit	46	Emerging	940	Python
16	George0828Zhang/torch_cif A fast parallel PyTorch implementation of the "CIF: Continuous...	46	Emerging	36	Python
17	by2101/OpenASR A pytorch based end2end speech recognition system.	45	Emerging	114	Python
18	theblackcat102/edgedict Working online speech recognition based on RNN Transducer. ( Trained model...	45	Emerging	292	Python
19	hirofumi0810/asr_preprocessing Python implementation of pre-processing for End-to-End speech recognition	44	Emerging	69	Python
20	upskyy/Transformer-Transducer PyTorch implementation of "Transformer Transducer: A Streamable Speech...	43	Emerging	113	Python
21	R1ckShi/AESRC2020 [ICASSP2021] Data preperation scripts, training pipeline and baseline...	43	Emerging	56	Python
22	ryanleary/patter speech-to-text in pytorch	43	Emerging	82	Python
23	kaituoxu/Speech-Transformer A PyTorch implementation of Speech Transformer, an End-to-End ASR with...	43	Emerging	809	Python
24	nobody132/masr 中文语音识别; Mandarin Automatic Speech Recognition;	43	Emerging	1,964	Python
25	jinserk/pytorch-asr ASR with PyTorch	42	Emerging	140	Python
26	charlesliucn/awesome-end2end-asr 💬 A list of End-to-End speech recognition, including papers, codes and other...	42	Emerging	52	—
27	pika-online/AESRC2020 a deep accent recognition network	41	Emerging	50	Python
28	declare-lab/speech-adapters Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient...	41	Emerging	42	Python
29	awslabs/speech-representations Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)	40	Emerging	104	Python
30	zh217/torch-asg Auto Segmentation Criterion (ASG) implemented in pytorch	40	Emerging	51	C++
31	tugstugi/mongolian-speech-recognition Mongolian speech recognition with PyTorch	40	Emerging	138	Python
32	1ytic/pytorch-edit-distance Levenshtein edit-distance on PyTorch and CUDA	40	Emerging	93	Cuda
33	sooftware/speech-transformer Transformer implementation speciaized in speech recognition tasks using Pytorch.	39	Emerging	65	Python
34	tabahi/contexless-phonemes-CUPE pytorch model for contexless-phoneme prediction from speech audio	39	Emerging	32	Python
35	1ytic/open_stt_e2e PyTorch end-to-end speech recognition	39	Emerging	49	Python
36	VITA-Group/Audio-Lottery [ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight,...	39	Emerging	32	Python
37	xingchensong/Speech-Transformer-tf2.0 transformer for ASR-systerm (via tensorflow2.0)	38	Emerging	114	Python
38	manhph2211/ViSR This repo builds an end-to-end deep learning application that supports...	38	Emerging	38	Jupyter Notebook
39	HawkAaron/E2E-ASR PyTorch Implementations for End-to-End Automatic Speech Recognition	38	Emerging	127	Python
40	HawkAaron/RNN-Transducer MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction...	38	Emerging	139	Python
41	stevenhillis/awesome-asr-contextualization A curated list of awesome papers on contextualizing E2E ASR outputs	37	Emerging	80	—
42	audioku/cross-accent-maml-asr Meta-learning model agnostic (MAML) implementation for cross-accented ASR	37	Emerging	45	Python
43	Sundy1219/eesen-for-thchs30 ASR for Chinese Mandarin	37	Emerging	76	Perl
44	GinoShun/Accent-Activation-Steering Official code for "Activation Steering for Accent Adaptation in Speech...	37	Emerging	3	Python
45	sooftware/lightning-asr Modular and extensible speech recognition library leveraging...	36	Emerging	50	Python
46	vectominist/MiniASR A mini, simple, and fast end-to-end automatic speech recognition toolkit.	36	Emerging	53	Jupyter Notebook
47	vectominist/spin Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for...	35	Emerging	64	Python
48	MingLunHan/CIF-PyTorch [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech...	35	Emerging	79	Python
49	sooftware/End-to-End-Speech-Recognition-Models PyTorch implementation of automatic speech recognition models.	35	Emerging	38	Python
50	cdyangbo/end2endASR implement end-to-end asr algorithm with tensorflow	34	Emerging	40	Python
51	jiwidi/DeepSpeech-pytorch Pytorch implementation for DeepSpeech 2.0	34	Emerging	31	Python
52	jindongwang/EasyEspnet Making Espnet easier to use	33	Emerging	54	Python
53	RF5/transfusion-asr Transcribing Speech with Multinomial Diffusion, training code and models.	33	Emerging	80	Python
54	mravanelli/pytorch_MLP_for_ASR This code implements a basic MLP for speech recognition. The MLP is trained...	33	Emerging	40	Perl
55	biyoml/End-to-End-Mandarin-ASR End-to-end speech recognition on AISHELL dataset.	32	Emerging	34	Python
56	DataXujing/ASR-paper :fire: ASR教程: https://dataxujing.github.io/ASR-paper/	32	Emerging	25	—
57	oleges1/quartznet-pytorch Quartznet implementation on pytorch [https://arxiv.org/abs/1910.10261]	32	Emerging	26	Jupyter Notebook
58	ondrejklejch/learning_to_adapt Coordinate-wise meta-learner for speaker adaptation of ASR models.	31	Emerging	20	Python
59	upskyy/ContextNet PyTorch implementation of "ContextNet: Improving Convolutional Neural...	31	Emerging	38	Python
60	vectominist/End-to-end-ASR-Pytorch-DLHLP Joint CTC-Attention End-to-end Speech Recognition - PyTorch Implementation...	30	Emerging	17	Python
61	clarinsi/Slovene_ASR_e2e Automatic Speech Recognition tool	30	Emerging	20	Python
62	nemoramo/acoustic_model This is a sub-repository in building to create acoustic model in Mandarin...	30	Emerging	6	Python
63	ThetaOne-AI/HiKE Hierarchical Korean-English Code-Switching Speech Recognition Benchmark...	28	Experimental	9	Python
64	daveshap/keras_asr ASR experiment using Google's Universal Sentence Encoder	27	Experimental	9	Jupyter Notebook
65	teamtee/LLM-ASR-Error-Correction This is a framework for using large language models to improve ASR...	26	Experimental	14	Python
66	emonosuke/emoASR End-to-end MOdeling of ASR (Automatic Speech Recognition)	26	Experimental	33	Python
67	aws-samples/seq2seq-asr-misbehaves Artifacts for the paper "Attentional Speech Recognition Models Misbehave on...	25	Experimental	3	—
68	aalto-speech/speechbrain-cl Implementation of different curriculum learning (CL) methods for...	25	Experimental	5	Python
69	PigeonDan1/ps-slm TASU: A New Style of Alignment of Speech LLM with only Text Training Data,...	25	Experimental	22	Python
70	kouyt5/lightning-asr 基于pytorch-lighting框架搭建的端到端语音识别模型，目前还在实验中，性能在不断优化	24	Experimental	4	Python
71	viig99/esolafast Fast C++ implementation of ESOLA using KFRLib, can be used for online...	24	Experimental	16	C++
72	tongjinle123/speech-transformer-pytorch_lightning ASR project with pytorch-lightning	24	Experimental	20	Python
73	vectominist/rspin Official inference code for NAACL 2024 paper "R-Spin: Efficient Speaker and...	24	Experimental	4	Python
74	DanielLin94144/Test-time-adaptation-ASR-SUTA Test-time adaptation for speech recognition model by single utterance. The...	23	Experimental	20	Python
75	biyoml/PyTorch-End-to-End-ASR-on-TIMIT Attention-based end-to-end ASR on TIMIT in PyTorch	23	Experimental	18	Python
76	shockless/asr-transformer Transformer for Automatic Speech Recognition	23	Experimental	2	Python
77	lucadellalib/ts-asr Target speaker automatic speech recognition (TS-ASR)	22	Experimental	12	Python
78	nttcslab-sp/torchain WIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)	22	Experimental	20	Python
79	dobby-seo/kosr Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)	21	Experimental	31	Python
80	1ytic/edit-distance-papers A curated list of papers dedicated to edit-distance as objective function	21	Experimental	53	—
81	SpringerNLP/Chapter12 Chapter 12: End-to-end Speech Recognition	21	Experimental	9	Jupyter Notebook
82	upskyy/Automatic-Speech-Recognition-Models End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.	21	Experimental	10	Python
83	yinruiqing/tiny-transducer Tiny Transducer: A Highly-Efficient Speech Recognition Model on Edge Devices	21	Experimental	26	Python
84	sunprinceS/MetaASR-CrossAccent Meta-Learning for End-to-End ASR	21	Experimental	10	Jupyter Notebook
85	Kirili4ik/QuartzNet-ASR-pytorch Automatic Speech Recognition (ASR) model QuartzNet trained on English...	20	Experimental	16	Jupyter Notebook
86	andybi7676/reborn-uasr REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training...	20	Experimental	14	Python
87	awasthiabhijeet/Error-Driven-ASR-Personalization Code for "Error-driven Fixed-Budget ASR Personalization for Accented...	20	Experimental	11	Python
88	erasedwalt/CTC-ASR An implementation of Jasper, QuartzNet, Citrinet and pipeline for training...	20	Experimental	12	Python
89	TeaPoly/AIF-PyTorch (NOT Official) Implementation Auto-regressive Integrate-and-Fire (AIF)	18	Experimental	5	Python
90	tuanio/deepspeech-ctc Deepspeech with ctc loss on Vivos Vietnamese Dataset	18	Experimental	6	Python
91	umitkacar/transformer-asr-transcription Real-time transformer-based ASR supporting 100+ languages - Google Cloud...	17	Experimental	2	Python
92	msalhab96/RNN-Transducer PyTorch implementation of Sequence Transduction with Recurrent Neural...	17	Experimental	15	Python
93	tuanio/e2e-asr-toolkit E2E Speech Recognition Toolkit with Hydra and Pytorch Lightning	17	Experimental	6	Python
94	gheyret/uyghur-asr-transformer Speech Recognition for Uyghur using Speech transformer	17	Experimental	28	Python
95	DuyguA/TSD2025-Mind-the-Gap Innovative ASR model to keep named entities intact, offered as a conference paper.	16	Experimental	1	Python
96	mict-zhaw/chall_e2e_stt End-to-end ASR experiments for language learning, focusing on...	16	Experimental	4	Python
97	AssemblyAI-Community/intro-to-espnet Getting Started with ESPnet \| AssemblyAI	15	Experimental	2	Python
98	Lakshmi-bashyam/NeuralLM2Arpa Implementation of conversion system : Neural Language models to backing off...	15	Experimental	2	Python
99	pragyak412/Improving-Voice-Separation-by-Incorporating-End-To-End-Speech-Recognition Implementing the paper -	15	Experimental	19	Python
100	chrarvi/automatic-speech-recognition An automatic speech recognition transformer for converting swedish voice to text.	14	Experimental	1	Python
101	AppleHolic/2020AIChallengeSpeechRecognition 2020 AI Challenge 음성 인식 코드	13	Experimental	8	Python
102	xingchensong/ASR-Wavnet some ASR-system implementations （via tensorflow 1.x）	13	Experimental	5	Python
103	MorrisXu-Driving/Improving_DeepSpeech_2_by_RNN_Transducer_Pytorch_Implementation In this repository, based on Deep Speech 2, two losses, CTC and RNN-T are compared.	13	Experimental	8	Python
104	shahad-mahmud/incremental_learning_for_asr Incremental learning for automatic speech recognition (ASR)	13	Experimental	8	Python
105	zyascend/End-to-End-Speech-Recognition-Learning ASR, End-to-End, end2end, Speech Recognition, 端到端语音识别	12	Experimental	12	—
106	upskyy/RNN-Transducer PyTorch Implementation of RNN-Transducer	12	Experimental	3	Python
107	khaykingleb/automatic-speech-recognition QuartzNet and DeepSpeech implementation for ASR	12	Experimental	4	Python
108	avrtt/MoE-speech-recognition Mixture of experts architecture for speech-to-text and language...	12	Experimental	3	Python
109	zw76859420/ASR_Transformer A Pytorch implementation of Speech Transformer, an End-to-End Automatic...	11	Experimental	2	—

Comparisons in this category

kospeech and openspeech (51 vs 48) end2end-asr-pytorch and OpenASR (48 vs 45)