Wav2Vec2 Speech Recognition Transformer Models

Fine-tuning and deployment of Wav2Vec2 models for automatic speech recognition (ASR) tasks, including multilingual and language-specific implementations. Does NOT include general speech-to-text pipelines, voice translation systems, or audio classification without ASR components.

There are 6 wav2vec2 speech recognition models tracked. The highest-rated is guxm2021/ALT_SpeechBrain at 36/100 with 49 stars.

Get all 6 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=wav2vec2-speech-recognition&limit=20"

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

# Model Score Tier
1 guxm2021/ALT_SpeechBrain

[ISMIR 2022] Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription

36
Emerging
2 subhasis-ai/Hindi-ASR-Wav2Vec2

This repository demonstrates development of Hindi ASR model using transformers.

23
Experimental
3 guxm2021/MM_ALT

[MM 2022] MM-ALT: A Multimodal Automatic Lyric Transcription System (Oral,...

22
Experimental
4 jvel07/wav2vec2_patho

Fine-tuning wav2vec2 to for Pathological Speech Processing

22
Experimental
5 hammaad2002/ASRAdversarialAttacks

An ASR (Automatic Speech Recognition) adversarial attack repository.

21
Experimental
6 maximkm/DLA_ASR_HW

ASR pytorch project

19
Experimental