Tensorflowasr

Release Notes

- Move dependencies to `requirements.txt`
- Add option to use loss scale in keras compile
- Add max lengths computation in ASR dataset
- Support TPU and static shape training

Release Notes

- Fixed rnnt loss in pure tf for batch size 1
- Update example configs

Release Notes

- Fix Transducer Batch Recognition
- Cast step to float32 in schedules
- Update create tfrecords and add subwords scripts

Release Notes

- Fix some minor bugs in dataset

Release Notes

- Update dataset config
- Update ASRDataset with option to use preprocessing in pure tf (not `tf.numpy_function`)
- Add Transducer Greedy Decoding V2 from [https://arxiv.org/pdf/1801.00841.pdf](https://arxiv.org/pdf/1801.00841.pdf)
- Update documents and results
- Update examples scripts to use new dataset config

Release Notes

- [x] Implement Slice Dataset that yield data in keras format `(x, y)`
- [x] Implement TFRecord Dataset that yield data in keras format `(x, y)`
- [x] Add new `RnntLoss` subclass of `tf.keras.losses.Loss` to use in `compile` function of `tf.keras.Model`
- [x] Add Transducer with custom `train_step` and `test_step` that uses `RnntLoss`
- [x] Add new `CtcLoss` subclass of `tf.keras.losses.Loss` to use in `compile` function of `tf.keras.Model`
- [x] Add CtcModel with custom `train_step` and `test_step` that uses `CtcLoss`