Python speech recognition library prints to the screen when recording audio Question: I am recording user’s voice using python speech_recognition library. The program shows a result even though I do not print it to the screen. How can I eliminate this? Asked By: İsmail Can Karataş || Source Answers: According to package github issue tracker …
Azure Pronunciation Assessment SDK return wrong result compare with api call Question: I’m using azure speech sdk to do pronunciation assessment, it works fine when i used api provide by azure, but when i use speech sdk the result is not correct. I follow the sample from cognitive services speech sdk Here is the code …
How do i ignore a the rest of a sentence that contains a word i want to print? Question: I’m trying to built an assistant, at first while I say "hi" it returns "hi" working great. but if I say "hi, what time is it" it goes to the first if cause it finds the …
How do I get my python virtual assistant to only listen once it hears a wake word? Question: I have a python virtual assistant that is always listening for commands. How can I make it so she only starts listening to commands once she hears the wake word such as Alexa, or in this case …
Not answering for a long time. speech_recognition Question: So i have this code that will listen to you speech recognition and and answer using pyttsx3 and openai but the problem is speech_recognition gets everything right but it will give errors if i say gibberish or just mute. can please help me. me no English code: …
tflite inference only predicts one label despite multiclass label training Question: I have trained a multiclass classifier for speech recognition using tensorflow. Then converted the model using tflite converter. The model can predict but it always outputs a single class. I suppose the problem is with the inference code because .h5 model can predict multiclass …
How to add custom terms to OpenAI's Whisper STT/ASR? Question: I have some domain specific jargon I would like Whisper to be able recognize. Is there a way, like Azure’s custom speech, or Google’s ASR, to add new terms to the system’s language model? Asked By: Erik Saltwell || Source Answers: Is there a way, …
Speech Recognition(IBM) username and password Question: I hope to use IBM speech recognition service without – curl or ibm_watson module. And my attempt is below: import speech_recognition as sr r = sr.Recognizer() text = r.recognize_ibm(audio,username=”,password=”) Even though, I have ‘Service credentials’ for IBM cloud – speech to text, I cannot find correct form for the …
why is my speech recognition not working in python Question: I am working on this project and its simply a desktop Assistant I am using speech recognition and pyttsx3 but the speech recognition is not working after the try nothing is executing it just jumps to except and passes can someone tell me why? and …
save microphone audio input when using azure speech to text Question: I’m currently using Azure speech to text in my project. It is recognizing speech input directly from microphone (which is what I want) and saving the text output, but I’m also interested in saving that audio input so that I can listen to it …
