TensorFlowASR v0.5.1

Release Notes

• Update base tester
• Update Transducer Models to use input_length instead of directly from output of Encoder (for using in batch testing)
• Fix typos

TensorFlowASR v0.5.0

Release Notes

• Supported ContextNet http://arxiv.org/abs/2005.03191
• Updated train dataset
• Updated example scripts
• Add tf.sequence_mask into Transducer Prediction Network while training to mask padding values

TensorFlowASR v0.4.5

Release Notes

• Add github publish workflow

TensorFlowASR v0.4.4

Release Notes

• Update transducer beam search to take norm_score
• Update base tester

TensorFlowASR v0.4.3

Release Notes

• Fix gammatone feature extraction for using in tf.function
• Add support for masking

TensorFlowASR v0.4.2

Release Notes

• Update audio read to convert from multi channels into single channel

TensorFlowASR v0.4.1

Release Notes

• Reformat code and fix minor bugs

TensorFlowASR v0.4.0

Release Notes

• 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.

TensorFlowASR v0.3.2

Release Notes

• Fix minor bugs in trainer

TensorFlowASR v0.3.1

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