Open Onotseike opened 6 years ago
@Onotseike
Hi Onotseike, you try this python3 script. It works for me.
# -*- coding: utf-8 -*-
def read_in_chunks(file_object, blocksize=1024, chunks=-1):
"""Lazy function (generator) to read a file piece by piece. Default chunk size: 1k."""
while chunks:
data = file_object.read(blocksize)
if not data:
break
yield data
chunks -= 1
import requests
YOUR_SUBSCRIPTION_KEY = ''
audiofile = 'whatstheweatherlike.wav'
headers = {
'Transfer-Encoding': 'chunked',
'Ocp-Apim-Subscription-Key': YOUR_SUBSCRIPTION_KEY,
'Content-type': 'audio/wav; codec=audio/pcm; samplerate=16000'
}
params = (
('language', 'en-us'),
('format', 'detailed'),
)
f = open(audiofile, 'rb')
response = requests.post('https://speech.platform.bing.com/speech/recognition/dictation/cognitiveservices/v1', headers=headers, params=params, data=read_in_chunks(f))
print(response.content)
Please is there a python implementation of STT similar to the TTS sample?