Fixed bug in stream processing to account correctly for receptive field of the model
use_chunking=True, the chunking method is actually used
Add speechRT model for low-latency speech predictions (decision latency <100ms)
Add new methods of processing -
process_audio_chunk- more suitable for analysing byte numpy arrays directly
Make the SDK thread-safe
The output of the
process_filefunction changed to align with the
process_streamfunction. For more information on the new output structure see https://sdk.oto.ai/docs/output-specification.
Performance bug in the output calculation
File processing results are now consistent with the streaming results
Typo in ‘GENDER_UNKOWN’ constant
Initial release with the Speech, Gender and Arousal models.