# Running the Spoken Digit Recognition Model Overview The example C++ application in this tutorial is called [snpe-net-run](https://docs.qualcomm.com/doc/80-63442-10/topic/SNPE_general_tools.html#snpe-net-run). It is a command line executable that executes a neural network using Qualcomm® Neural Processing SDK APIs. The required arguments to snpe-net-run are: - A neural network model in the DLC file format - An input list file with paths to the input data. Optional arguments to snpe-net-run are: - Choice of GPU or DSP runtime (default is CPU) - Output directory (default is ./output) - Show help description snpe-net-run creates and populates an output directory with the results of executing the neural network on the input data. ![../images/neural_network.png](data:image/png;base64,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) The Qualcomm® Neural Processing SDK provides Linux and Android binaries of **snpe-net-run** under - $SNPE\_ROOT/bin/x86\_64-linux-clang - $SNPE\_ROOT/bin/aarch64-android - $SNPE\_ROOT/bin/aarch64-oe-linux-gcc8.2 - $SNPE\_ROOT/bin/aarch64-oe-linux-gcc9.3 Introduction This chapter will show an example of recognizing the 10 classes in the free spoken digit dataset, with data processing and a 4-layer neural network, through Qualcomm® Neural Processing SDK. The step-by-step example will create, train, convert, and execute a TensorFlow-Keras audio model with Qualcomm® Neural Processing SDK. As a prerequisite, users should download the **Free SpokenDigit Dataset (FSDD)**. cd $SNPE_ROOT/examples/Models/spoken_digit git clone https://github.com/Jakobovski/free-spoken-digit-dataset Copy to clipboard The external python3 packages required for this example are: - librosa (0.10.2) - tensorflow (2.10.1) There are five files and a single directory in the $SNPE\_ROOT/examples/Models/spoken\_digit folder - free-spoken-digit-dataset (download from git) - input\_list.txt - interpretRawDNNOutput.py - processSpokenDigitInput.py - spoken\_digit.py - NOTICE.txt The **interpretRawDNNOutput.py** will translate Qualcomm® Neural Processing SDK output and display the prediction. The **processSpokenDigitInput.py** processes user input wav audio file into raw format for snpe-net-run. The **spoken\_digit.py** python3 script creates and trains a 5-layer neural network model. After training is done, the corresponding frozen protobuf file will be generated. The **free-spoken-digit-dataset** directory is the dataset downloaded by the user. Prerequisites - The Qualcomm® Neural Processing SDK has been set up following the [Qualcomm (R) Neural Processing SDK Setup](https://docs.qualcomm.com/doc/80-63442-10/topic/SNPE_general_setup.html) chapter. - The [Tutorials Setup](https://docs.qualcomm.com/doc/80-63442-10/topic/tutorial_setup.html) has been completed. - TensorFlow is installed (see [TensorFlow Setup](https://docs.qualcomm.com/doc/80-63442-10/topic/SNPE_general_setup.html#tensorflow-setup)) Create, Train, and Convert Spoken Digit Model Run spoken\_digit.py to create and train the Word-RNN model. cd $SNPE_ROOT/examples/Models/spoken_digit python3 spoken_digit.py Copy to clipboard The terminal will show the following messages. Successfully split free-spoken-digit-dataset training/testing data. Training data created. Epoch 1/20 4/4 [==============================] - 1s 142ms/step - loss: 30.2495 - accuracy: 0.1328 - val_loss: 25.0048 - val_accuracy: 0.1406 Epoch 2/20 4/4 [==============================] - 0s 42ms/step - loss: 16.7755 - accuracy: 0.1680 - val_loss: 10.5915 - val_accuracy: 0.1680 Epoch 3/20 4/4 [==============================] - 0s 44ms/step - loss: 9.0951 - accuracy: 0.1504 - val_loss: 8.5512 - val_accuracy: 0.1641 ... ... ... Epoch 18/20 4/4 [==============================] - 0s 31ms/step - loss: 0.2890 - accuracy: 0.9297 - val_loss: 1.8068 - val_accuracy: 0.6504 Epoch 19/20 4/4 [==============================] - 0s 28ms/step - loss: 0.2399 - accuracy: 0.9336 - val_loss: 1.7628 - val_accuracy: 0.6602 Epoch 20/20 4/4 [==============================] - 0s 29ms/step - loss: 0.2024 - accuracy: 0.9512 - val_loss: 1.7234 - val_accuracy: 0.6777 Optimization done. Save frozen graph in spoken_digit.pb. Copy to clipboard Next, convert the frozen graph model with snpe-tensorflow-to-dlc. snpe-tensorflow-to-dlc --input_network model/spoken_digit.pb \ --input_dim x "1, 10, 35" \ --out_node "Identity \ --output_path spoken_digit.dlc Copy to clipboard After DLC conversion, we can view the converted dlc architecture with **snpe-dlc-info** and **snpe-dlc-viewer** as follows: snpe-dlc-info -i spoken_digit.dlc Copy to clipboard The output will be: ------------------------------------------------------------------------------------------------------------------------------------------------------------- | Id | Name | Type | Inputs | Outputs | Out Dims | Runtimes | Parameters | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | 0 | sequential/dense/Tensordot/transpose | Transpose | x:0 (data type: Float_32; tensor dimension: [1,10,35]; tensor type: APP_WRITE) [NW Input] | sequential/dense/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,35]; tensor type: NATIVE) | 1x10x35 | A D G C | packageName: qti.aisw | | | | | | | | | perm: [0, 1, 2] | | 1 | sequential/dense/Tensordot/Reshape:0 | Reshape | sequential/dense/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,35]; tensor type: NATIVE) | sequential/dense/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,35]; tensor type: NATIVE) | 10x35 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [10, 35] | | 2 | sequential/dense/Tensordot/MatMul | FullyConnected | sequential/dense/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,35]; tensor type: NATIVE) | sequential/dense/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,256]; tensor type: NATIVE) | 10x256 | A D G C | bias_op_name: sequential/dense/BiasAdd | | | | | sequential/dense/Tensordot/ReadVariableOp:0 (data type: Float_32; tensor dimension: [256,35]; tensor type: STATIC) | | | | packageName: qti.aisw | | | | | sequential/dense/BiasAdd/ReadVariableOp:0 (data type: Float_32; tensor dimension: [256]; tensor type: STATIC) | | | | param count: 9k (16.2%) | | | | | | | | | MACs per inference: 8k (15.9%) | | 3 | sequential/dense/BiasAdd:0 | Reshape | sequential/dense/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,256]; tensor type: NATIVE) | sequential/dense/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,256]; tensor type: NATIVE) | 1x10x256 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [1, 10, 256] | | 4 | sequential/dense/Relu | ElementWiseNeuron | sequential/dense/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,256]; tensor type: NATIVE) | sequential/dense_1/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,256]; tensor type: NATIVE) | 1x10x256 | A D G C | operation: 4 | | | | | | | | | packageName: qti.aisw | | 5 | sequential/dense_1/Tensordot/Reshape:0 | Reshape | sequential/dense_1/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,256]; tensor type: NATIVE) | sequential/dense_1/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,256]; tensor type: NATIVE) | 10x256 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [10, 256] | | 6 | sequential/dense_1/Tensordot/MatMul | FullyConnected | sequential/dense_1/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,256]; tensor type: NATIVE) | sequential/dense_1/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,128]; tensor type: NATIVE) | 10x128 | A D G C | bias_op_name: sequential/dense_1/BiasAdd | | | | | sequential/dense_1/Tensordot/ReadVariableOp:0 (data type: Float_32; tensor dimension: [128,256]; tensor type: STATIC) | | | | packageName: qti.aisw | | | | | sequential/dense_1/BiasAdd/ReadVariableOp:0 (data type: Float_32; tensor dimension: [128]; tensor type: STATIC) | | | | param count: 32k (57.9%) | | | | | | | | | MACs per inference: 32k (58.2%) | | 7 | sequential/dense_1/BiasAdd:0 | Reshape | sequential/dense_1/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,128]; tensor type: NATIVE) | sequential/dense_1/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,128]; tensor type: NATIVE) | 1x10x128 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [1, 10, 128] | | 8 | sequential/dense_1/Relu | ElementWiseNeuron | sequential/dense_1/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,128]; tensor type: NATIVE) | sequential/dense_2/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,128]; tensor type: NATIVE) | 1x10x128 | A D G C | operation: 4 | | | | | | | | | packageName: qti.aisw | | 9 | sequential/dense_2/Tensordot/Reshape:0 | Reshape | sequential/dense_2/Tensordot/transpose:0 (data type: Float_32; tensor dimension: [1,10,128]; tensor type: NATIVE) | sequential/dense_2/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,128]; tensor type: NATIVE) | 10x128 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [10, 128] | | 10 | sequential/dense_2/Tensordot/MatMul | FullyConnected | sequential/dense_2/Tensordot/Reshape:0 (data type: Float_32; tensor dimension: [10,128]; tensor type: NATIVE) | sequential/dense_2/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,64]; tensor type: NATIVE) | 10x64 | A D G C | bias_op_name: sequential/dense_2/BiasAdd | | | | | sequential/dense_2/Tensordot/ReadVariableOp:0 (data type: Float_32; tensor dimension: [64,128]; tensor type: STATIC) | | | | packageName: qti.aisw | | | | | sequential/dense_2/BiasAdd/ReadVariableOp:0 (data type: Float_32; tensor dimension: [64]; tensor type: STATIC) | | | | param count: 8k (14.5%) | | | | | | | | | MACs per inference: 8k (14.5%) | | 11 | sequential/dense_2/BiasAdd:0 | Reshape | sequential/dense_2/Tensordot/MatMul:0 (data type: Float_32; tensor dimension: [10,64]; tensor type: NATIVE) | sequential/dense_2/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,64]; tensor type: NATIVE) | 1x10x64 | A D G C | packageName: qti.aisw | | | | | | | | | shape: [1, 10, 64] | | 12 | sequential/dense_2/Relu | ElementWiseNeuron | sequential/dense_2/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10,64]; tensor type: NATIVE) | sequential/dense_2/Relu:0 (data type: Float_32; tensor dimension: [1,10,64]; tensor type: NATIVE) | 1x10x64 | A D G C | operation: 4 | | | | | | | | | packageName: qti.aisw | | 13 | sequential/dense_3/MatMul | FullyConnected | sequential/dense_2/Relu:0 (data type: Float_32; tensor dimension: [1,10,64]; tensor type: NATIVE) | sequential/dense_3/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10]; tensor type: NATIVE) | 1x10 | A D G C | bias_op_name: sequential/dense_3/BiasAdd | | | | | sequential/dense_3/MatMul/ReadVariableOp:0 (data type: Float_32; tensor dimension: [10,640]; tensor type: STATIC) | | | | packageName: qti.aisw | | | | | sequential/dense_3/BiasAdd/ReadVariableOp:0 (data type: Float_32; tensor dimension: [10]; tensor type: STATIC) | | | | param count: 6k (11.3%) | | | | | | | | | MACs per inference: 6k (11.4%) | | 14 | sequential/dense_3/Softmax | Softmax | sequential/dense_3/BiasAdd:0 (data type: Float_32; tensor dimension: [1,10]; tensor type: NATIVE) | Identity:0 (data type: Float_32; tensor dimension: [1,10]; tensor type: APP_READ) | 1x10 | A D G C | axis: 1 | | | | | | | | | beta: 1 | | | | | | | | | packageName: qti.aisw | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Copy to clipboard snpe-dlc-viewer -i spoken_digit.dlc Copy to clipboard The output network model HTML file will be saved at /tmp/spoken\_digit.html. Run on Linux Host First, **processSpokenDigitInput.py** script needs to be run in order to process the audio input data **test/5\_jackson\_0.wav** to raw format. The output name will be **input.raw** python3 processSpokenDigitInput.py test/5_jackson_0.wav Copy to clipboard Next, run **snpe-net-run** to get the inference result. snpe-net-run --container spoken_digit.dlc --input_list input_list.txt Copy to clipboard After snpe-net-run completes, verify that the results are populated in the $SNPE\_ROOT/examples/Models/spoken\_digit/output directory. There should be one or more .log files and several Result\_X directories. The raw output prediction will be located in $SNPE\_ROOT/examples/Models/spoken\_digit/output/Result\_0/output/Result\_0/Identity:0.raw. It holds the output tensor data of 10 probabilities for the 10 categories. The element with the highest value represents the top classification. We can use a python3 script to interpret the classification results as follows: python3 interpretRawDNNOutput.py output/Result_0/Identity:0.raw Copy to clipboard The output should look like the following, showing classification results for all the images. 0 : 0.000110 1 : 0.012185 2 : 0.000011 3 : 0.000593 4 : 0.002053 5 : 0.814478 6 : 0.002425 7 : 0.043664 8 : 0.003228 9 : 0.121254 Classification Result: Class 5. Copy to clipboard The final output shows the audio file was classified as “Class 5” (from a total of 10 labels) with a probability of 0.814478. Look at the rest of the output to see the model’s classification on other classes. **Binary data input** Note that the spoken digit classification model does not accept wav files as input. The model expects its input tensor dimension to be **1 x 10 x 35** as a float array. The processSpokenDigitInput.py script performs a wav to binary data conversion. The script is an example of how wav audio files can be preprocessed to generate input for the classification model. Run on Target Platform ( Android/LE/UBUN ) **Select target architecture** Qualcomm® Neural Processing SDK provides binaries for different target platforms. Android binaries are compiled with clang using libc++ STL implementation. Below are examples for aarch64-android (Android platform) and aarch64-oe-linux-gcc11.2 toolchain (LE platform). Similarly other toolchains for different platforms can be set as SNPE\_TARGET\_ARCH # For Android targets: architecture: arm64-v8a - compiler: clang - STL: libc++ export SNPE_TARGET_ARCH=aarch64-android # Example for LE targets export SNPE_TARGET_ARCH=aarch64-oe-linux-gcc11.2 Copy to clipboard For simplicity, this tutorial sets the target binaries to aarch64-android. **Push libraries and binaries to target** Push Qualcomm® Neural Processing SDK libraries and the prebuilt snpe-net-run executable to /data/local/tmp/snpeexample on the Android target. Set SNPE\_TARGET\_DSPARCH to the DSP architecture of the target Android device. export SNPE_TARGET_ARCH=aarch64-android export SNPE_TARGET_DSPARCH=hexagon-v73 adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin" adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib" adb shell "mkdir -p /data/local/tmp/snpeexample/dsp/lib" adb push $SNPE_ROOT/lib/$SNPE_TARGET_ARCH/*.so \ /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib adb push $SNPE_ROOT/lib/$SNPE_TARGET_DSPARCH/unsigned/*.so \ /data/local/tmp/snpeexample/dsp/lib adb push $SNPE_ROOT/bin/$SNPE_TARGET_ARCH/snpe-net-run \ /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin Copy to clipboard **Set up enviroment variables** Set up the library path, the path variable, and the target architecture in adb shell to run the executable with the -h argument to see its description. adb shell export SNPE_TARGET_ARCH=aarch64-android export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin snpe-net-run -h exit Copy to clipboard **Push model data to Android target** To execute the spoken digit classification model on your Android target follow these steps: adb shell "mkdir -p /data/local/tmp/spoken_digit" adb push input.raw /data/local/tmp/spoken_digit adb push input_list.txt /data/local/tmp/spoken_digit adb push spoken_digit.dlc /data/local/tmp/spoken_digit Copy to clipboard **Note:** It may take some time to push the DLC file to your target. Running on Android using CPU Runtime Run the Android C++ executable with the following commands: adb shell export SNPE_TARGET_ARCH=aarch64-android export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin cd /data/local/tmp/spoken_digit snpe-net-run --container spoken_digit.dlc --input_list input_list.txt exit Copy to clipboard The executable will create the results folder: /data/local/tmp/spoken\_digit/output. To pull the output: adb pull /data/local/tmp/spoken_digit/output output_android Copy to clipboard Check the classification results by running the interpret python3 script. python3 interpretRawDNNOutput.py output_android/Result_0/Identity:0.raw Copy to clipboard The output should look like the following, showing classification results for all the images. 0 : 0.000110 1 : 0.012185 2 : 0.000011 3 : 0.000593 4 : 0.002053 5 : 0.814478 6 : 0.002425 7 : 0.043664 8 : 0.003228 9 : 0.121254 Classification Result: Class 5. Copy to clipboard Running on Android using GPU Runtime Try running on an Android target with the **–use\_gpu** option as follows. By default, the GPU runtime runs in GPU\_FLOAT32\_16\_HYBRID (math: full float and data storage: half float) mode. We can change the mode to GPU\_FLOAT16 (math: half float and data storage: half float) using **–gpu\_mode** option. adb shell export SNPE_TARGET_ARCH=aarch64-android export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin cd /data/local/tmp/spoken_digit snpe-net-run --container spoken_digit.dlc --input_list input_list.txt --use_gpu exit Copy to clipboard Pull the output into an output\_android\_gpu directory. adb pull /data/local/tmp/spoken_digit/output output_android_gpu Copy to clipboard Again, we can run the interpret script to see the classification results. python3 interpretRawDNNOutput.py output_android_gpu/Result_0/Identity:0.raw Copy to clipboard The output should look like the following, showing classification results for all the images. 0 : 0.000113 1 : 0.012330 2 : 0.000011 3 : 0.000604 4 : 0.002087 5 : 0.813591 6 : 0.002461 7 : 0.043883 8 : 0.003279 9 : 0.121640 Classification Result: Class 5. Copy to clipboard Review the output for the classification results. Classification results are identical to the run with CPU runtime, but there are differences in the probabilities associated with the output labels due to floating point precision differences. Last Published: Jun 04, 2026 [Previous Topic Running the Word-RNN Model](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/tutorial_word_rnn.md) [Next Topic Running a VGG Model](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/tutorial_onnx.md)