v0.60.0

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

LICENSE

@@ -0,0 +1 @@
+The license of the original trained model can be found at https://github.com/SeanNaren/deepspeech.pytorch/blob/master/LICENCE.

README.md

@@ -0,0 +1,86 @@
+---
+library_name: pytorch
+license: other
+tags:
+- foundation
+- real_time
+- android
+pipeline_tag: automatic-speech-recognition
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/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/blob/v0.60.0/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.com) 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://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deepspeech2/releases/v0.60.0/deepspeech2-tflite-float.zip)
+
+For more device-specific assets and performance metrics, visit **[DeepSpeech2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deepspeech2)**.
+
+
+### Option 2: Export with Custom Configurations
+
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/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/blob/v0.60.0/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 | 4387.282 ms | 147 - 160 MB | CPU
+| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5872.379 ms | 205 - 220 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12161.223 ms | 67 - 551 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 18819.817 ms | 109 - 118 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4150.669 ms | 49 - 62 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® SA8775P | 14169.392 ms | 107 - 117 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® SA8650P | 14169.392 ms | 107 - 117 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® SA8255P | 14169.392 ms | 107 - 117 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® QCS8450 | 5872.379 ms | 205 - 220 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5239.743 ms | 66 - 550 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3156.583 ms | 30 - 43 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® SA7255P | 18819.817 ms | 109 - 118 MB | CPU
+| DeepSpeech2 | TFLITE | float | Qualcomm® SA8295P | 9438.743 ms | 97 - 107 MB | CPU
+| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Elite Mobile | 3156.583 ms | 30 - 43 MB | CPU
+| DeepSpeech2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3371.983 ms | 108 - 121 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
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) 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).

release_assets.json

@@ -0,0 +1,13 @@
+{
+    "version": "0.60.0",
+    "precisions": {
+        "float": {
+            "universal_assets": {
+                "tflite": {
+                    "tool_versions": {},
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deepspeech2/releases/v0.60.0/deepspeech2-tflite-float.zip"
+                }
+            }
+        }
+    }
+}