EasyNLPnlp-191

Speech Token Frame Rate

Problem

Return how many frames per second a speech tokenizer produces: sample_rate / hop_length, where hop_length is the frame hop in samples.

Hint

A smaller hop length gives a higher frame rate.

case 1

in: [16000,160]

expected: 100

case 2

in: [16000,320]

expected: 50

case 3

in: [8000,80]

expected: 100

case 4

in: [22050,256]

expected: 86.1328125

Starter codePython

def speech_token_frame_rate(sample_rate, hop_length):
    # Your code here
    pass

4 test cases · run your code against them in the editor