speech_recognition

speech_recognition copied to clipboard

Google_speech_recognition WinError 10060

2

Simple code: `import speech_recognition as sr r = sr.Recognizer() with sr.Microphone() as source: print("Say something!") audio = r.listen(source) print(r.recognize_google(audio))` Error: TimeoutError: [WinError 10060] A connection attempt failed because the connected...

pmtkachev

Facing problem related pyaudio installation

3

I'm constantly getting this error. Please give me suggestions. Defaulting to user installation because normal site-packages is not writeable Collecting pyaudio Using cached PyAudio-0.2.11.tar.gz (37 kB) Preparing metadata (setup.py) ......

Smruti1998

Facing issues in installing pyaudio

2

I'm constantly getting this error, please give me solution for this, Defaulting to user installation because normal site-packages is not writeable Collecting pyaudio Using cached PyAudio-0.2.11.tar.gz (37 kB) Preparing metadata...

Smruti1998

recognize_google should have pfilter = 0 by default but it's censoring words as if it's running pfilter = 1

3

Steps to reproduce ------------------ ``` def speech_to_text(self): recognizer = sr.Recognizer() with sr.Microphone() as mic: print("listening...") recognizer.adjust_for_ambient_noise(mic,duration=2) audio = recognizer.listen(mic) try: self.text = recognizer.recognize_google(audio, language = "en-US") print(text) ``` "what the...

blu3str

Using SpeechRecognition on a Raspberry Pi 400 doesn't work

1

Steps to reproduce ------------------ As far as I'm aware, just trying to use the library on the raspberry pi causes issues. This was the code I used: import speech_recognition as...

Bradams2212

ModuleNotFoundError: No module named 'speech_recognition' in Fedora 26

36

I already installed `speech_recognition` and trying to import `speech_recognition` it gave me `ModuleNotFoundError: No module named 'speech_recognition'` **Hear is my python code** ``` import speech_recognition as sr r = sr.Recognizer()...

rajnishcoder

For the VOSK model to work, the model must be downloaded into the working directory. This requirement is incompatible with projects that utilize a different directory structure. I am adding...

andrastaus

Timestamps for detected words?

1

For transcriptions with a souce audio file, is there any way to return timestamps for words detected by the recognizer? (Eg. if it detected 'mistake' at 1m:03s of the audio...

sarabande98

speech_recognition grabbing audio from Zoom calls

2

Hello A user on Stack Overflow (not me) has reported a problem with speech_recognition grabbing the audio from a Zoom call if you run a script whilst on Zoom: https://stackoverflow.com/questions/66251391/python-speech-recognition-library-causes-speaker-output-from-discord-or-zoom-t...

donquibeats

There's any way to .listen audio from Speaker, not Microphone?

1

Im developing a autoresponding SIP-bot (Session Initiation Protocol), which can transcribe audio input from user which other side of connection. There's any way, how I can redirect _**audio stream from...

canaldkz