Open Amarta113 opened 1 month ago
Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! π
Are you using any dataset for this project? If yes, please share it. Also what are the deep learning models you are planning to implement here for this problem statement?
@abhisheks008 I had not used any dataset. I used "whisper-large-v3" model for speech to text and "llama3-8b-8192" model to answer queries with groq API and gtts library for text to speech.
Any other models which will compete the whisper architecture?
I used API therefore only whisper was available. Here is the documentation link
It is streamlit application
Only implementing whisper will not qualify for this repository. You need to come up with at least 3 models for any problem statement. @Amarta113
@abhisheks008 I also used llama3 for q&a and for text to speech I used google tts library which contains two algorithms Tacotron and WaveNet .
@abhisheks008 I also used llama3 for q&a and for text to speech I used google tts library which contains two algorithms Tacotron and WaveNet .
Cool I am assigning this issue to you. Make sure you complete it by today 6 PM IST.
Deep Learning Simplified Repository (Proposing new issue)
:red_circle: Project Title : Hindi Voice Assistant :red_circle: Aim : To develop a chatbot that takes input in hindi audio and give output in hindi text and audio :red_circle: Dataset : :red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.
π Follow the Guidelines to Contribute in the Project :
requirements.txt
- This file will contain the required packages/libraries to run the project in other machines.Model
folder, theREADME.md
file must be filled up properly, with proper visualizations and conclusions.:red_circle::yellow_circle: Points to Note :
:white_check_mark: To be Mentioned while taking the issue :
Happy Contributing π
All the best. Enjoy your open source journey ahead. π