Metadata-Version: 2.1
Name: nemo-asr
Version: 0.8
Summary: Collection of Neural Modules for Speech Recognition
Home-page: https://github.com/nvidia/nemo
Author: NVIDIA
Author-email: nemo-toolkit@nvidia.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: License :: OSI Approved :: Apache Software License
Description-Content-Type: text/markdown
Requires-Dist: nemo-toolkit
Requires-Dist: librosa
Requires-Dist: num2words
Requires-Dist: inflect
Requires-Dist: torch-stft
Requires-Dist: soundfile
Requires-Dist: marshmallow
Requires-Dist: ruamel.yaml
Requires-Dist: sox

NeMo ASR Collection: Neural Modules for Automatic Speech Recognition
====================================================================

**Models**

The NeMo ASR collection currently has modules for building
1. All Jasper convolutional models:
..* Jasper DR 10x5
..* Jasper 15x5 Seperable
..* Jasper Mini
2. Jasper Encoder + Seq2seq Decoder

See the documentation and tutorials for ``nemo_asr`` [here](https://nvidia.github.io/NeMo/asr/intro.html).

