Skip to content

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

License

Notifications You must be signed in to change notification settings

Hassan-Zaib/TensorFlowASR

 
 

Repository files navigation

Getting started with TensorFlow ASR

Create conda env

conda activate asr_25
pip install -r requirements.txt
python scripts/create_librispeech_trans.py --dir /mydata/hassan/data/LibriSpeech/dev-clean/ /mydata/hassan/data/LibriSpeech/dev-clean/transcript.tsv # Optional
python scripts/create_librispeech_trans.py --dir /mydata/hassan/data/LibriSpeech/train-clean-100/ /mydata/hassan/data/LibriSpeech/train-clean-100/transcript.tsv # Optional
python scripts/create_librispeech_trans.py --dir /mydata/hassan/data/LibriSpeech/test-clean/ /mydata/hassan/data/LibriSpeech/test-clean/transcript.tsv
Python examples/conformer/test.py —saved /path/to/latest.h5

About

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

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 97.6%
  • Python 2.4%