TensorFlowASR v0.8.0

Release Notes

• Update stft
• Update WER and CER Metrics

TensorFlowASR v0.7.8

Release Notes

• Fix duplicate log softmax in rnnt loss in tf

TensorFlowASR v0.7.7

Release Notes

• Support for infinite dataset (for using steps_per_execution)
• Support for storing hdf5 to cloud
• Update training script using keras builtin functions

TensorFlowASR v0.7.6

Release Notes

• Replace max lengths by metadata to store other dataset information, such as number of entries
• Update TPU example script to use steps_per_execution

TensorFlowASR v0.7.5

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

TensorFlowASR v0.7.4

Release Notes

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

TensorFlowASR v0.7.3

Release Notes

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

TensorFlowASR v0.7.2

Release Notes

• Fix some minor bugs in dataset

TensorFlowASR v0.7.1

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
• Update documents and results
• Update examples scripts to use new dataset config

TensorFlowASR v0.7.0

Release Notes

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