# TensorSpeech/TensorFlowASR

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

Repository: https://github.com/TensorSpeech/TensorFlowASR
Canonical: https://ross.abutalabs.com/products/tensorflowasr
Homepage: https://huylenguyen.com/asr
Language: Python
License: Apache-2.0
License Family: permissive
Topics: automatic-speech-recognition, deepspeech2, speech-recognition, speech-to-text, tensorflow2, rnn-transducer, conformer, tflite, tflite-model, tflite-convertion, ctc, tensorflow, subword-speech-recognition, end2end, contextnet, jasper, streaming-transducer
Last push: 2026-08-05T07:38:46+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 8, longevity 100
- inputs: {"age_days": 2393, "days_push": 28, "days_rel": 448, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1010, forks 238 (observed 2026-08-28T04:03:13.014931+00:00)

## What it is
TensorFlowASR is a Python library implementing automatic speech recognition architectures such as DeepSpeech2, Jasper, RNN Transducer, ContextNet, and Conformer in TensorFlow 2. Models can be trained on custom corpora and converted to TFLite for lightweight deployment.

## Use cases
- convert speech to text with tensorflow
- train a conformer asr model
- build a streaming speech recognition model
- convert asr model to tflite for mobile
- train deepspeech2 on custom dataset
- speech recognition with rnn transducer loss

## When to choose
- you want to train or fine-tune ASR models in TensorFlow 2
- you need TFLite export for on-device speech recognition
- you want transducer or CTC architectures with subword support

## When to avoid
- you prefer PyTorch-based ASR toolkits
- you only need a pretrained plug-and-play transcription API without training

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, deep-learning, audio-processing
- domain: speech-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: tensorflow, asr, speech-to-text, conformer, rnn-transducer, ctc, tflite, deepspeech2, contextnet, jasper, streaming, natural-language-processing, gpu

## Member repositories
- TensorSpeech/TensorFlowASR (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:13.014931+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 2026-08-30T07:11:55.642872+00:00, confidence not recorded.
  - readme: https://github.com/TensorSpeech/TensorFlowASR (fetched 2026-08-28T04:03:13.014931+00:00, sha 2ccd6cfb8dc0)
  - homepage: https://huylenguyen.com/asr (fetched 2026-08-29T13:11:51.697148+00:00, sha 077df35b3fb9)
  - registry_pypi: https://pypi.org/pypi/tensorflowasr/json (fetched 2026-08-29T13:11:51.699736+00:00, sha c318091a2217)
- Data as of 2026-08-30T08:39:29.467469+00:00.