- Updated RNN Transducer Beam Search from pure python operation to tf operations - Updated Test runner to accept batch size > 1 - Updated Test datasets to return signals instead of speech features - Updated Conformer's Model Config names - Updated recognize functions to accept signals instead of speech features - Updated readme files.
0.3.2
Release Notes
- Fix minor bugs in trainer
0.3.1
Release Notes
- Add `additional_properties` fields to config, in order for users to use their own extra configs - Remove `tensorflow>=2.3.0` required dependency for more flexible installation
0.3.0
Release Notes
- Fix conformer tflite on tf-nightly - Supported Gradients Accumulation for Training in Larger Batch Size
0.2.10
Release Notes
- Reduce differences between `librosa.stft` and `tf.signal.stft`
0.2.9
Release Notes
- Update configurations from dictionary to class - Update Deep Speech 2 - Supported Jasper - Add optimizer config to Streaming Transducer Example