TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
Implements multiple end-to-end architectures including Conformer, ContextNet, and RNN Transducer using both CTC and RNNT loss functions for training. Supports TFLite conversion to reduce model size for edge deployment, with built-in audio feature extraction and augmentation pipelines. Provides pre-trained models and training examples across multiple languages including English and Vietnamese datasets.
1,005 stars and 930 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
1,005
Forks
240
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 11, 2025
Monthly downloads
930
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TensorSpeech/TensorFlowASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
sooftware/kospeech
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
hirofumi0810/neural_sp
End-to-end ASR/LM implementation with PyTorch