# pannous/tensorflow-speech-recognition

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

Repository: https://github.com/pannous/tensorflow-speech-recognition
Canonical: https://ross.abutalabs.com/products/tensorflow-speech-recognition
Language: Python
License: NOASSERTION
License Family: other
Topics: tensorflow, speech-recognition, neural-network, deep-learning, stt, speech-to-text
Last push: 2024-01-17T14:27:13+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3922, "days_push": 959, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2173, forks 628 (observed 2026-08-28T04:06:21.935352+00:00)

## What it is
An educational repository demonstrating speech recognition with TensorFlow using sequence-to-sequence neural networks. The project is explicitly deprecated and maintained only for learning purposes, with the README recommending Whisper or DeepSpeech instead.

## Use cases
- learn how speech-to-text models work with seq2seq networks
- study spectrogram-based audio classification in TensorFlow
- find example code for training speech recognition models
- understand LSTM and densenet architectures for audio
- explore speech data augmentation techniques

## When to choose
- you want to study how speech recognition was built with older TensorFlow 1.x
- you need educational toy examples like number or speaker classifiers
- you are learning sequence-to-sequence concepts applied to audio

## When to avoid
- you need a production speech-to-text system
- you want up-to-date TensorFlow compatibility
- you need state-of-the-art accuracy - use Whisper or DeepSpeech instead

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: speech-recognition, machine-learning, deep-learning
- domain: speech-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: speech-to-text, tensorflow, sequence-to-sequence, educational, deprecated, linux

## Member repositories
- pannous/tensorflow-speech-recognition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.935352+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:49:03.013571+00:00, confidence not recorded.
  - readme: https://github.com/pannous/tensorflow-speech-recognition (fetched 2026-08-28T04:06:21.935352+00:00, sha 02f3f3b9dab7)
- Data as of 2026-08-30T08:39:29.467469+00:00.