---
title: DeepSpeech2
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/DeepSpeech2"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/DeepSpeech2.md"
repository: Qualcomm-AI-Hub/DeepSpeech2
last_updated: 2026-10-16
license: apache-2.0
downloads: 0
stars: 0
tags:
  - foundation
  - real_time
  - android
---

# DeepSpeech2

> DeepSpeech2 - Qualcomm-AI-Hub 在 ModelScope 开源的模型。DeepSpeech2: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/DeepSpeech2 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: Qualcomm-AI-Hub/DeepSpeech2
- **License**: apache-2.0
- **Tags**: foundation, real_time, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/DeepSpeech2

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/deepspeech2/web-assets/model_demo.png)

# DeepSpeech2: Optimized for Qualcomm Devices

DeepSpeech2 is an end-to-end automatic speech recognition (ASR) model. It uses convolutional layers for feature extraction followed by bidirectional recurrent layers and CTC for sequence-to-sequence learning.

This is based on the implementation of DeepSpeech2 found [here](https://github.com/SeanNaren/deepspeech.pytorch).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/deepspeech2) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started
There are two ways to deploy this model on your device:

### Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| TFLITE | float | Universal |  | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/deepspeech2/releases/v0.62.1/deepspeech2-tflite-float.zip)

For more device-specific assets and performance metrics, visit **[DeepSpeech2 on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/deepspeech2)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/deepspeech2) Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for [DeepSpeech2 on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/deepspeech2) for usage instructions.

## Model Details

**Model Type:** Model_use_case.speech_recognition

**Model Stats:**
- Input resolution: Spectrogram (800 frames x 161 features)
- Model size: 330.48MB
- Number of parameters: 94.6M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4197.771 ms | 103 - 110 MB | CPU
| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5789.207 ms | 184 - 199 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12353.042 ms | 66 - 551 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4072.02 ms | 79 - 82 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® SA8775P | 14827.141 ms | 109 - 119 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® SA8650P | 14827.141 ms | 109 - 119 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® SA8255P | 14827.141 ms | 109 - 119 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® QCS8450 | 5789.207 ms | 184 - 199 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5188.277 ms | 65 - 549 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3077.222 ms | 33 - 47 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® SA7255P | 18159.336 ms | 102 - 112 MB | CPU
| DeepSpeech2 | TFLITE | float | Qualcomm® SA8295P | 9275.238 ms | 100 - 110 MB | CPU
| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Elite Mobile | 3077.222 ms | 33 - 47 MB | CPU
| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3211.287 ms | 111 - 124 MB | CPU

## License
* The license for the original implementation of DeepSpeech2 can be found
  [here](https://github.com/SeanNaren/deepspeech.pytorch/blob/master/LICENCE).

## References
* [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://arxiv.org/abs/1512.02595)
* [Source Model Implementation](https://github.com/SeanNaren/deepspeech.pytorch)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).