GitHub - KarolSekscinski/speech2text: ASR project to learn tensorflow. Model trained on Common Voice Mozilla Dataset in GCP.

KarolSekscinski / speech2text Public

ASR project to learn tensorflow. Model trained on Common Voice Mozilla Dataset in GCP.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 70 Commits
Datasets		Datasets
Models		Models
soundutils		soundutils
.gitignore		.gitignore
cloud_utils.py		cloud_utils.py
configs.py		configs.py
inference_model.py		inference_model.py
model.py		model.py
mp3_to_wav_converter.py		mp3_to_wav_converter.py
requirements.txt		requirements.txt
setup.sh		setup.sh
setup_tensorflow_gpu.sh		setup_tensorflow_gpu.sh
test_train.py		test_train.py
train.py		train.py
verify_files.py		verify_files.py