Audi support from issue

[ajitesh123]

Add the ability for users to provide audio input for their performance reviews and self-reviews. Previously, users had to type their input, but now they can record their audio. You can use streamlit audio-record (https://github.com/stefanrmmr/streamlit-audio-recorder) for this.

The audio should be converted from speech to text using the Whisper model on Groq library (https://console.groq.com/docs/speech-text), and the resulting text will be used as input to the review generation process.\n\nMain Changes:

• Add streamlit audio-record app.py
• Implemented the convert_speech_to_text function using Whisper model in Groq
• Updated the ReviewRequest and SelfReviewRequest models to include an optional audio_review field and add to prompt for LLM to use it for generating review and self-review
• Don't make changed to fastapi endpoint (app.fastapi.py file) for now.",

[greptile-apps]

Implementation Steps

1. Add Streamlit Audio Recorder in app.py:

import streamlit as st
from streamlit_audio_recorder import audio_recorder

# Inside the Performance Review section
if review_type == "Performance Review":
    st.title("Write Performance Review in a Minute")

    audio_review = audio_recorder()
    if audio_review:
        audio_text = convert_speech_to_text(audio_review)
        st.text_area('Audio Review Text', value=audio_text, height=200)

    # Existing code...

2. Implement convert_speech_to_text function in llm.py:

class GroqLLM(LLM):
    # Existing code...

    def convert_speech_to_text(self, audio_data: bytes) -> str:
        response = self.client.speech_to_text(audio_data)
        return response['text']

3. Update ReviewRequest and SelfReviewRequest models in review.py and self_review.py:

class ReviewRequest(BaseModel):
    # Existing fields...
    audio_review: Optional[bytes] = None

class SelfReviewRequest(BaseModel):
    # Existing fields...
    audio_review: Optional[bytes] = None

4. Modify prompt generation to include audio_review in review.py and self_review.py:

def generate_prompt(your_role, candidate_role, perf_question, your_review, audio_review=None):
    if audio_review:
        your_review += f"\n\nAudio Review: {audio_review}"
    # Existing code...

def generate_self_review_prompt(text_dump, questions, instructions, audio_review=None):
    if audio_review:
        text_dump += f"\n\nAudio Review: {audio_review}"
    # Existing code...

References

/app.py
/llm.py
/review.py
/self_review.py

About Greptile

This response provides a starting point for your research, not a precise solution.

Help us improve! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

Ask Greptile · Edit Issue Bot Settings