speech_recognition
speech_recognition copied to clipboard
Uberi
Speech recognition module for Python, supporting several engines and APIs, online and offline.
``` import speech_recognition as sr r = sr.Recognizer() with sr.Microphone() as source: r.adjust_for_ambient_noise(source, duration = 5) print("listening...") # read the audio data from the default microphone audio_data = r.record(source, duration=5)...
Steps to reproduce ------------------ 1. Everytime I run this code: `import speech_recognition as sr import time import gpiozero as gpio led = gpio.PWMLED(27) r = sr.Recognizer() def Recognize(): with sr.Microphone()...
It's killing me that a simple example of pyaudio couldn't work. I'm trying to record my voice using pyaudio like this: ``` import pyaudio import wave CHUNK = 1024 FORMAT...
* Fixed region bucket parameter configuration, adding the parameter `CreateBucketConfiguration={'LocationConstraint': region}` to the bucket creation call; * Added language parameter on `start_transcription_job`. It was fixed on `en-US`; * Removed unused...
I use speech_recognition and use PC's default MIC for record. When record I use record and listen function. Normally my function works well but sometime, it can't record with prblem:...
I use speech_recognition with a Virtual Cable ([https://vb-audio.com/Cable/](https://vb-audio.com/Cable/)). The issue is speech_recogniton captures a very distorted sound regardless if I speak or not. Recorded Sound [Headphone warning]: [https://youtu.be/q78puE0Tdjc](https://youtu.be/q78puE0Tdjc) However, this...
listen API currently does not provide a way to specify sample rate. It seems that it uses some non standard sample rate / wave.getframerate() of 44100 which is making it...
Steps to reproduce ------------------ I saw in the examples section the following [one]:(https://github.com/Uberi/speech_recognition/blob/master/examples/tensorflow_commands.py) where tensor-flow method of Recognizer is used. (example in master branch) I jumped to definition of the...
Expected behaviour ------------------ When speaking in english, recognize_whisper_api should transcribe text in english Actual behaviour ---------------- When speaking long enough phrases, the api automatically translates to Italian (I'm in Italy),...
Add a new 'params' parameter to the 'recognize_whisper_api' function, which allows the transcription prompt to be set by passing 'prompt='. This was implemented by passing the 'params' parameter to the...
