Hugging Face's logo

qualcomm
/
Whisper-Base-En

Automatic Speech Recognition
PyTorch
LiteRT
ONNX
foundation
android
Model card Files Community
1

Whisper-Base-En: Optimized for Mobile Deployment

Automatic speech recognition (ASR) model for English transcription as well as translation

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-Base-En found here.

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

Model Details

  • Model Type: Speech recognition
  • Model Stats:
    • Model checkpoint: base.en
    • Input resolution: 80x3000 (30 seconds audio)
    • Mean decoded sequence length: 112 tokens
    • Number of parameters (WhisperEncoder): 23.7M
    • Model size (WhisperEncoder): 90.6 MB
    • Number of parameters (WhisperDecoder): 48.6M
    • Model size (WhisperDecoder): 186 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
WhisperDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 9.829 ms 5 - 26 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 4.542 ms 18 - 20 MB FP16 NPU Whisper-Base-En.so
WhisperDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 13.868 ms 16 - 294 MB FP16 NPU Whisper-Base-En.onnx
WhisperDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 7.654 ms 13 - 126 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 3.355 ms 41 - 61 MB FP16 NPU Whisper-Base-En.so
WhisperDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 10.817 ms 52 - 122 MB FP16 NPU Whisper-Base-En.onnx
WhisperDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 7.277 ms 5 - 115 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 3.485 ms 20 - 87 MB FP16 NPU Use Export Script
WhisperDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 10.054 ms 52 - 114 MB FP16 NPU Whisper-Base-En.onnx
WhisperDecoder SA7255P ADP SA7255P TFLITE 36.431 ms 6 - 112 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder SA7255P ADP SA7255P QNN 26.407 ms 18 - 27 MB FP16 NPU Use Export Script
WhisperDecoder SA8255 (Proxy) SA8255P Proxy TFLITE 9.875 ms 5 - 27 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder SA8255 (Proxy) SA8255P Proxy QNN 4.395 ms 20 - 22 MB FP16 NPU Use Export Script
WhisperDecoder SA8295P ADP SA8295P TFLITE 12.265 ms 0 - 98 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder SA8295P ADP SA8295P QNN 5.712 ms 18 - 35 MB FP16 NPU Use Export Script
WhisperDecoder SA8650 (Proxy) SA8650P Proxy TFLITE 9.887 ms 5 - 28 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder SA8650 (Proxy) SA8650P Proxy QNN 4.199 ms 20 - 23 MB FP16 NPU Use Export Script
WhisperDecoder SA8775P ADP SA8775P TFLITE 12.431 ms 5 - 112 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder SA8775P ADP SA8775P QNN 5.327 ms 18 - 27 MB FP16 NPU Use Export Script
WhisperDecoder QCS8275 (Proxy) QCS8275 Proxy TFLITE 36.431 ms 6 - 112 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder QCS8275 (Proxy) QCS8275 Proxy QNN 26.407 ms 18 - 27 MB FP16 NPU Use Export Script
WhisperDecoder QCS8550 (Proxy) QCS8550 Proxy TFLITE 9.824 ms 5 - 30 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder QCS8550 (Proxy) QCS8550 Proxy QNN 4.267 ms 20 - 22 MB FP16 NPU Use Export Script
WhisperDecoder QCS9075 (Proxy) QCS9075 Proxy TFLITE 12.431 ms 5 - 112 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder QCS9075 (Proxy) QCS9075 Proxy QNN 5.327 ms 18 - 27 MB FP16 NPU Use Export Script
WhisperDecoder QCS8450 (Proxy) QCS8450 Proxy TFLITE 12.142 ms 5 - 116 MB FP16 NPU Whisper-Base-En.tflite
WhisperDecoder QCS8450 (Proxy) QCS8450 Proxy QNN 6.874 ms 20 - 89 MB FP16 NPU Use Export Script
WhisperDecoder Snapdragon X Elite CRD Snapdragon® X Elite QNN 3.765 ms 20 - 20 MB FP16 NPU Use Export Script
WhisperDecoder Snapdragon X Elite CRD Snapdragon® X Elite ONNX 12.093 ms 107 - 107 MB FP16 NPU Whisper-Base-En.onnx
WhisperEncoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 199.056 ms 0 - 75 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 252.347 ms 1 - 3 MB FP16 NPU Whisper-Base-En.so
WhisperEncoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 295.512 ms 54 - 564 MB FP16 NPU Whisper-Base-En.onnx
WhisperEncoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 176.369 ms 39 - 81 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 160.252 ms 1 - 19 MB FP16 NPU Whisper-Base-En.so
WhisperEncoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 244.67 ms 71 - 1525 MB FP16 NPU Whisper-Base-En.onnx
WhisperEncoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 157.268 ms 39 - 67 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 165.673 ms 0 - 1390 MB FP16 NPU Use Export Script
WhisperEncoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 331.668 ms 73 - 1532 MB FP16 NPU Whisper-Base-En.onnx
WhisperEncoder SA7255P ADP SA7255P TFLITE 1163.651 ms 30 - 54 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder SA7255P ADP SA7255P QNN 1009.943 ms 1 - 10 MB FP16 NPU Use Export Script
WhisperEncoder SA8255 (Proxy) SA8255P Proxy TFLITE 198.905 ms 0 - 65 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder SA8255 (Proxy) SA8255P Proxy QNN 249.979 ms 1 - 3 MB FP16 NPU Use Export Script
WhisperEncoder SA8295P ADP SA8295P TFLITE 206.932 ms 38 - 69 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder SA8295P ADP SA8295P QNN 219.218 ms 1 - 17 MB FP16 NPU Use Export Script
WhisperEncoder SA8650 (Proxy) SA8650P Proxy TFLITE 205.514 ms 0 - 57 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder SA8650 (Proxy) SA8650P Proxy QNN 208.878 ms 1 - 3 MB FP16 NPU Use Export Script
WhisperEncoder SA8775P ADP SA8775P TFLITE 365.876 ms 38 - 63 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder SA8775P ADP SA8775P QNN 216.546 ms 1 - 11 MB FP16 NPU Use Export Script
WhisperEncoder QCS8275 (Proxy) QCS8275 Proxy TFLITE 1163.651 ms 30 - 54 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder QCS8275 (Proxy) QCS8275 Proxy QNN 1009.943 ms 1 - 10 MB FP16 NPU Use Export Script
WhisperEncoder QCS8550 (Proxy) QCS8550 Proxy TFLITE 205.363 ms 0 - 33 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder QCS8550 (Proxy) QCS8550 Proxy QNN 225.859 ms 1 - 3 MB FP16 NPU Use Export Script
WhisperEncoder QCS9075 (Proxy) QCS9075 Proxy TFLITE 365.876 ms 38 - 63 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder QCS9075 (Proxy) QCS9075 Proxy QNN 216.546 ms 1 - 11 MB FP16 NPU Use Export Script
WhisperEncoder QCS8450 (Proxy) QCS8450 Proxy TFLITE 609.548 ms 38 - 86 MB FP16 GPU Whisper-Base-En.tflite
WhisperEncoder QCS8450 (Proxy) QCS8450 Proxy QNN 353.514 ms 1 - 1440 MB FP16 NPU Use Export Script
WhisperEncoder Snapdragon X Elite CRD Snapdragon® X Elite QNN 174.657 ms 0 - 0 MB FP16 NPU Use Export Script
WhisperEncoder Snapdragon X Elite CRD Snapdragon® X Elite ONNX 284.386 ms 133 - 133 MB FP16 NPU Whisper-Base-En.onnx

Installation

Install the package via pip:

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

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_base_en.demo

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

NOTE: If you want running 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_base_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_base_en.export

Profiling Results
------------------------------------------------------------
WhisperDecoder
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 9.8                    
Estimated peak memory usage (MB): [5, 26]                
Total # Ops                     : 983                    
Compute Unit(s)                 : NPU (983 ops)          

------------------------------------------------------------
WhisperEncoder
Device                          : Samsung Galaxy S23 (13)   
Runtime                         : TFLITE                    
Estimated inference time (ms)   : 199.1                     
Estimated peak memory usage (MB): [0, 75]                   
Total # Ops                     : 419                       
Compute Unit(s)                 : GPU (408 ops) CPU (11 ops)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

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

# Load the model
model = Model.from_pretrained()
decoder_model = model.decoder
encoder_model = model.encoder

# Device
device = hub.Device("Samsung Galaxy S23")

# Trace model
decoder_input_shape = decoder_model.get_input_spec()
decoder_sample_inputs = decoder_model.sample_inputs()

traced_decoder_model = torch.jit.trace(decoder_model, [torch.tensor(data[0]) for _, data in decoder_sample_inputs.items()])

# Compile model on a specific device
decoder_compile_job = hub.submit_compile_job(
    model=traced_decoder_model ,
    device=device,
    input_specs=decoder_model.get_input_spec(),
)

# Get target model to run on-device
decoder_target_model = decoder_compile_job.get_target_model()
# Trace model
encoder_input_shape = encoder_model.get_input_spec()
encoder_sample_inputs = encoder_model.sample_inputs()

traced_encoder_model = torch.jit.trace(encoder_model, [torch.tensor(data[0]) for _, data in encoder_sample_inputs.items()])

# Compile model on a specific device
encoder_compile_job = hub.submit_compile_job(
    model=traced_encoder_model ,
    device=device,
    input_specs=encoder_model.get_input_spec(),
)

# Get target model to run on-device
encoder_target_model = encoder_compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

decoder_profile_job = hub.submit_profile_job(
    model=decoder_target_model,
    device=device,
)
encoder_profile_job = hub.submit_profile_job(
    model=encoder_target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

decoder_input_data = decoder_model.sample_inputs()
decoder_inference_job = hub.submit_inference_job(
    model=decoder_target_model,
    device=device,
    inputs=decoder_input_data,
)
decoder_inference_job.download_output_data()
encoder_input_data = encoder_model.sample_inputs()
encoder_inference_job = hub.submit_inference_job(
    model=encoder_target_model,
    device=device,
    inputs=encoder_input_data,
)
encoder_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.

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

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 provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

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

License

  • The license for the original implementation of Whisper-Base-En can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Automatic Speech Recognition
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support automatic-speech-recognition models for pytorch library.