jerivl / Deepcut

A robot that raps
Apache License 2.0
1 stars 1 forks source link

Split audio array based on list of intervals #5

Open jerivl opened 4 years ago

jerivl commented 4 years ago

Issue: TTS will output a long sentence, and forced allignment will give the time intervals of syllables. Need to chop sentence into syllables

Task: Partition a long segment of audio based on list of time intervals provided

Desired input: Numpy array of audio data (sentence), sample rate, time intervals

Desired output: List of numpy arrays of containing split audio data