tensorflow-ctc-speech-recognition and kaggle_speech_recognition

These are ecosystem siblings—both are independent implementations of the CTC-based speech recognition architecture using TensorFlow, serving as reference implementations or learning resources for the same algorithmic approach rather than tools meant to be used together or as alternatives to each other.

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 9/25
Maturity 16/25
Community 19/25
Stars: 131
Forks: 47
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 72
Forks: 20
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About tensorflow-ctc-speech-recognition

philipperemy/tensorflow-ctc-speech-recognition

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).

Uses LSTM networks with CTC loss to decode speech directly to text, trained and evaluated on the VCTK Corpus with configurable batch sizes and network architectures. Extracts audio features via librosa and python_speech_features, then feeds spectrograms through recurrent layers followed by CTC decoding to handle variable-length audio-text alignment without explicit frame-level annotations. Demonstrates end-to-end training on single-speaker subsets, showing reasonable generalization despite limited data through techniques like random silence truncation for realistic validation.

About kaggle_speech_recognition

huschen/kaggle_speech_recognition

Conv-LSTM-CTC speech recognition network (end-to-end), written in TensorFlow.

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