Excellent work. Are you going to modify this so it can be utilized on mobile devices? Also, have you put your code in a public repository so people can try it out?
I made is so that you have to press the button every time you need to chat by voice ... this is just a prototype ... a lot of work needed ... I've moved on to build agents every since ... plz checkout the new vids ...
hi, i need a local model ai for convert audio to text. i give a video and it gives me transcript. i am using currently subtitle edit but this software isn't accurate. i can use whisper models but i don't know how can i download its files. for persian (farsi) language. - what model do you suggest me? - is there any tutorial for installing this model on my computer? i need to use ai for convert audio to text accurate in my language. thanks.
I'm currently planning a course on Ollama models that run locally ... still researching ... but Whisper works great for what you're trying to do ... you can use something like this to turn the text into a downloadable file: def save_text_to_file(text, file_name="translated_text.txt"): # Write the text to a file with open(file_name, "w", encoding="utf-8") as file: file.write(text) print(f"File saved as {file_name}") # Example usage: extracted_text = "This is the translated text extracted from the video." save_text_to_file(extracted_text, "extracted_text.txt")
Excellent work. Are you going to modify this so it can be utilized on mobile devices? Also, have you put your code in a public repository so people can try it out?
github.com/ahmedmusawir/voice-chatbot-python-streamlit
awesome...thanks
@HTMLFiveDev When we ask the question it is automatically getting closed and the model is just greeting, some where need to change?
I made is so that you have to press the button every time you need to chat by voice ... this is just a prototype ... a lot of work needed ... I've moved on to build agents every since ... plz checkout the new vids ...
hi, i need a local model ai for convert audio to text. i give a video and it gives me transcript. i am using currently subtitle edit but this software isn't accurate. i can use whisper models but i don't know how can i download its files.
for persian (farsi) language.
- what model do you suggest me?
- is there any tutorial for installing this model on my computer? i need to use ai for convert audio to text accurate in my language.
thanks.
I'm currently planning a course on Ollama models that run locally ... still researching ... but Whisper works great for what you're trying to do ... you can use something like this to turn the text into a downloadable file:
def save_text_to_file(text, file_name="translated_text.txt"):
# Write the text to a file
with open(file_name, "w", encoding="utf-8") as file:
file.write(text)
print(f"File saved as {file_name}")
# Example usage:
extracted_text = "This is the translated text extracted from the video."
save_text_to_file(extracted_text, "extracted_text.txt")
Git hub link?
github.com/ahmedmusawir/voice-chatbot-python-streamlit