Wav2vec2 Python Packages

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit

espnet-s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit

paddlespeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

jabberjay

🦜 Synthetic Voice Detection

paddlespeech-feat

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

openpronounce

Open-source phoneme-level English pronunciation assessment (Wav2Vec2 + DTW). Self-hosted alternative to Azure Pronunciation Assessment.

paddleaudio

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

paddlespeech-ctcdecoders

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

ovos-stt-plugin-wav2vec

A wav2vec stt plugin for OVOS

kfa

A fast Khmer Forced Aligner powered by Wav2Vec2CTC and Phonetisaurus

asr-attacks

An ASR (Automatic Speech Recognition) adversarial attack repository.

mimora

Free, fully local pronunciation trainer for English and Spanish. TTS, speech recognition, phrase generation and scoring all run on your machine.

mapss-measures

The code for the MAPSS measures for source separation evaluation (ICLR, 2026)

phonomatch

Local speech-to-IPA recognition and vocabulary matching with lexicon-constrained phrase decoding.

asr-attack

Adversarial robustness toolkit for Hugging Face ASR. FGSM, PGD, noise and environmental attacks behind one API across Whisper, wav2vec2, HuBERT and MMS, with benchmark reports in HTML and JSON. On PyPI.

asrbench-cli

A command-line tool for the ASRBench framework, simplifying audio transcription system benchmarking with a single config file, supporting popular and custom transcription systems

indicasr

Speeech Recognition for Indic languages.

vid2cleantxt

Python API & command-line tool to easily transcribe speech-based video files into clean text

paddlespeech-ldd-ctcdecoders

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.