Whisper Tiny En

🚀 Whisper-Tiny-En: Optimized for Mobile Deployment

Automatic speech recognition (ASR) model for English transcription as well as translation. It's a state - of - the - art system that transcribes spoken language into written text, performing well in noisy environments and excelling at long - form transcription.

OpenAI’s Whisper ASR (Automatic Speech Recognition) model is a state - of - the - art system designed for transcribing spoken language into written text. It exhibits robust performance in realistic, noisy environments, making it highly reliable for real - world applications. Specifically, it excels in long - form transcription, capable of accurately transcribing audio clips up to 30 seconds long. Time to the first token is the encoder's latency, while time to each additional token is decoder's latency, where we assume a mean decoded length specified below.

This model is an implementation of Whisper - Tiny - En found here.

This repository provides scripts to run Whisper - Tiny - En on Qualcomm® devices. More details on model performance across various devices can be found here.

✨ Features

• High - Performance ASR: OpenAI’s Whisper ASR model offers excellent performance in transcribing spoken language, especially in noisy real - world scenarios.
• Long - Form Transcription: Capable of accurately transcribing audio clips up to 30 seconds long.
• Mobile Deployment: Optimized for deployment on Qualcomm® devices.

📦 Installation

Install the package via pip:

pip install "qai - hub - models[whisper - tiny - en]"

💻 Usage Examples

Basic Usage

Configure Qualcomm® AI Hub to run this model on a cloud - hosted device

Sign - in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in, navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud - hosted devices.

qai - hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end - to - end demo that downloads pre - trained weights and runs this model on a sample input.

python -m qai_hub_models.models.whisper_tiny_en.demo

The above demo runs a reference implementation of pre - processing, model inference, and post - processing.

⚠️ Important Note

If you want to run in a Jupyter Notebook or Google Colab - like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.whisper_tiny_en.demo

Run model on a cloud - hosted device

In addition to the demo, you can also run the model on a cloud - hosted Qualcomm® device. This script does the following:

• Performance check on - device on a cloud - hosted device
• Downloads compiled assets that can be deployed on - device for Android.
• Accuracy check between PyTorch and on - device outputs.

python -m qai_hub_models.models.whisper_tiny_en.export

Profiling Results
------------------------------------------------------------
WhisperEncoderInf
Device                          : cs_8275 (ANDROID 14)                  
Runtime                         : TFLITE                                
Estimated inference time (ms)   : 419.3                                 
Estimated peak memory usage (MB): [20, 42]                              
Total # Ops                     : 271                                   
Compute Unit(s)                 : npu (0 ops) gpu (260 ops) cpu (11 ops)

------------------------------------------------------------
WhisperDecoderInf
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 6.9                                  
Estimated peak memory usage (MB): [3, 70]                              
Total # Ops                     : 557                                  
Compute Unit(s)                 : npu (557 ops) gpu (0 ops) cpu (0 ops)

Advanced Usage

How does this work?

This [export script](https://aihub.qualcomm.com/models/whisper_tiny_en/qai_hub_models/models/Whisper - Tiny - En/export.py) leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on - device. Let's go through each step below in detail:

Step 1: Compile model for on - device deployment

import torch

import qai_hub as hub
from qai_hub_models.models.whisper_tiny_en import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on - device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud - hosted device

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)
        

Step 3: Verify on - device accuracy

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

⚠️ Important Note

This on - device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

📚 Documentation

Model Details

Model Performance Table

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

• TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.
• QNN (.so export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80 - 63442 - 50/sample_app.html) provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Whisper - Tiny - En's performance across various devices here. Explore all available models on Qualcomm® AI Hub

📄 License

• The license for the original implementation of Whisper - Tiny - En can be found here.
• The license for the compiled assets for on - device deployment can be found [here](https://qaihub - public - assets.s3.us - west - 2.amazonaws.com/qai - hub - models/Qualcomm+AI+Hub+Proprietary+License.pdf)

References

• Robust Speech Recognition via Large - Scale Weak Supervision
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on - device AI.
• For questions or feedback please [reach out to us](mailto:ai - hub - support@qti.qualcomm.com).