end2end-asr-pytorch and OpenASR

These are competitors—both implement end-to-end ASR architectures in PyTorch with similar scope, so users would select one based on architecture preference (e.g., attention-based vs. CTC) and code maturity rather than using them together.

end2end-asr-pytorch
48
Emerging
OpenASR
45
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 9/25
Maturity 16/25
Community 20/25
Stars: 304
Forks: 62
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 114
Forks: 24
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About end2end-asr-pytorch

gentaiscool/end2end-asr-pytorch

End-to-End Automatic Speech Recognition on PyTorch

Implements a low-rank Transformer encoder-decoder architecture with optional CNN feature extractors (VGG or embedding-based) for sequence-to-sequence ASR. Supports multi-GPU batch parallelization and flexible training across multiple datasets with configurable beam-search decoding, achieving 13.5% CER on Mandarin Chinese with beam width 8. Compatible with PyTorch and torchaudio, accepts custom datasets via CSV manifests with character-level labeling.

About OpenASR

by2101/OpenASR

A pytorch based end2end speech recognition system.

Scores updated daily from GitHub, PyPI, and npm data. How scores work