Changelog¶
0.6.0¶
Fixed Bugs¶
Fixed bug in stream processing to account correctly for receptive field of the model
When
use_chunking=True
, the chunking method is actually used
Features¶
Add speechRT model for low-latency speech predictions (decision latency <100ms)
Add new methods of processing -
process_audio_bytes
,process_audio_chunk
- more suitable for analysing byte numpy arrays directlyMake the SDK thread-safe
0.5.0¶
Breaking Changes¶
The output of the
process_file
function changed to align with theprocess_stream
function. For more information on the new output structure see https://sdk.oto.ai/docs/output-specification.
Fixed Bugs¶
Performance bug in the output calculation
File processing results are now consistent with the streaming results
Typo in ‘GENDER_UNKOWN’ constant
0.4.0¶
Initial release with the Speech, Gender and Arousal models.