Closed absin1 closed 5 years ago
I am using an audio file from RAVEDESS dataset:
I do ffmpeg -i /home/absin/Downloads/03-01-01-01-01-01-01.wav
and get this:
Input #0, wav, from '/home/absin/Downloads/03-01-01-01-01-01-01.wav':
Metadata:
encoded_by : Adobe Systems Inc
encoder : Adobe Premiere Pro CS6 (Macintosh)
date : 2013-11-02
creation_time : 19:55:37
time_reference : 360360
Duration: 00:00:03.30, bitrate: 909 kb/s
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 48000 Hz, 1 channels, s16, 768 kb/s
Thanks for pointing out the issue @absin1
Do you mind following the documentation over at: https://docs.deepaffects.com/docs/emotion-recognition-api.html
We're in the process of removing stale documents from this repo.
Let me know if you face any issues.
Thanks @sushant-hiray
I have an incoming audio 16 bit PCM, is there a chunk_generator_from_stream
like there are chunk_generator_from_file
and chunk_generator_from_url
.
I am following this. But I get the following error:
What could be the problem?