Sign inSign up

opea/audioqna

By opea

•Updated 6 months ago

Audioqna gateway. Using language modeling to generate answers to user queries by converting audio in

Image
Machine learning & AI
Data science
0

10K+

opea/audioqna repository overview

⁠AudioQnA Application

AudioQnA is an example that demonstrates the integration of Generative AI (GenAI) models for performing question-answering (QnA) on audio files, with the added functionality of Text-to-Speech (TTS) for generating spoken responses. The example showcases how to convert audio input to text using Automatic Speech Recognition (ASR), generate answers to user queries using a language model, and then convert those answers back to speech using Text-to-Speech (TTS).

⁠Table of Contents

  1. Architecture⁠
  2. Deployment Options⁠

⁠Architecture

The AudioQnA example is implemented using the component-level microservices defined in GenAIComps⁠. The flow chart below shows the information flow between different microservices for this example.

---
config:
  flowchart:
    nodeSpacing: 400
    rankSpacing: 100
    curve: linear
  themeVariables:
    fontSize: 50px
---
flowchart LR
    %% Colors %%
    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
    classDef invisible fill:transparent,stroke:transparent;
    style AudioQnA-MegaService stroke:#000000

    %% Subgraphs %%
    subgraph AudioQnA-MegaService["AudioQnA MegaService "]
        direction LR
        ASR([ASR MicroService]):::blue
        LLM([LLM MicroService]):::blue
        TTS([TTS MicroService]):::blue
    end
    subgraph UserInterface[" User Interface "]
        direction LR
        a([User Input Query]):::orchid
        UI([UI server<br>]):::orchid
    end



    WSP_SRV{{whisper service<br>}}
    SPC_SRV{{speecht5 service <br>}}
    LLM_gen{{LLM Service <br>}}
    GW([AudioQnA GateWay<br>]):::orange


    %% Questions interaction
    direction LR
    a[User Audio Query] --> UI
    UI --> GW
    GW <==> AudioQnA-MegaService
    ASR ==> LLM
    LLM ==> TTS

    %% Embedding service flow
    direction LR
    ASR <-.-> WSP_SRV
    LLM <-.-> LLM_gen
    TTS <-.-> SPC_SRV

⁠Deployment Options

The table below lists currently available deployment options. They outline in detail the implementation of this example on selected hardware.

⁠Validated Configurations

Deploy MethodLLM EngineLLM ModelHardware
Docker ComposevLLM, TGImeta-llama/Meta-Llama-3-8B-InstructIntel Gaudi
Docker ComposevLLM, TGI, GPT-SoVITSmeta-llama/Meta-Llama-3-8B-InstructIntel Xeon
Docker ComposevLLM, TGImeta-llama/Meta-Llama-3-8B-InstructAMD EPYC
Docker ComposevLLM, TGIIntel/neural-chat-7b-v3-3AMD ROCm
Helm ChartsvLLM, TGImeta-llama/Meta-Llama-3-8B-InstructIntel Gaudi
Helm ChartsvLLM, TGImeta-llama/Meta-Llama-3-8B-InstructIntel Xeon

Tag summary

Content type

Image

Digest

sha256:c0219d0b4…

Size

157.8 MB

Last updated

6 months ago

docker pull opea/audioqna