Changelog¶
0.7.0¶
Fixed Bugs¶
Remove unnecessary tensorflow log lines
Features¶
Add emotions model for emotions classification
Update to tensorflow 2.3
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.