[Python] Python TensorFlow Speech Recognition -1073741819 (0xC0000005) Error

I'm working on a speech recognition project using TensorFlow in Python. Normally, TensorFlow can only be used with a CPU or an NVIDIA GPU. I have an AMD Radeon 7600S GPU. Because of this, I installed the tensorflow-directml-plugin developed by Microsoft, which allowed it to detect my AMD GPU. However, I'm currently facing another issue. I run my code, the necessary dataset for my model downloads, and the model is trained. But after training, during the testing phase, I get the following error:

2025-08-22 19:29:27.611794: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:272] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 13875 MB memory) -> physical PluggableDevice (device: 0, name: DML, pci bus id: <undefined>)
63/63 [==============================] - 9s 136ms/step - loss: 14.5690 - accuracy: 0.1045 - val_loss: 2.4005 - val_accuracy: 0.1140
Epoch 2/5
63/63 [==============================] - 8s 132ms/step - loss: 2.4516 - accuracy: 0.1370 - val_loss: 2.1963 - val_accuracy: 0.1560
Epoch 3/5
63/63 [==============================] - 8s 122ms/step - loss: 2.2549 - accuracy: 0.1680 - val_loss: 2.1321 - val_accuracy: 0.2320
Epoch 4/5
63/63 [==============================] - 2s 32ms/step - loss: 2.1942 - accuracy: 0.2035 - val_loss: 2.0759 - val_accuracy: 0.2540
Epoch 5/5
63/63 [==============================] - 4s 56ms/step - loss: 2.1982 - accuracy: 0.2075 - val_loss: 2.0824 - val_accuracy: 0.2440
Model kaydedildi: spoken_digit_model.keras
2025-08-22 19:29:49.644711: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:306] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.
2025-08-22 19:29:49.645238: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:272] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 13875 MB memory) -> physical PluggableDevice (device: 0, name: DML, pci bus id: <undefined>)

Process finished with exit code -1073741819 (0xC0000005)


I've researched the causes of this error but haven't been able to find a clear solution. I'll provide my code below. Any help would be greatly appreciated. Thank you in advance.

My code:

import os
import tensorflow as tf
import tensorflow_datasets as tfds
import numpy as np


(ds_train_full,), ds_info = tfds.load(
'spoken_digit',
split=['train'],
as_supervised=True,
with_info=True
)

commands = ds_info.features['label'].names
num_classes = len(commands)
print("Tanınacak komutlar:", commands)


dataset_size = ds_info.splits['train'].num_examples
train_size = int(0.8 * dataset_size)

ds_train = ds_train_full.take(train_size)
ds_test = ds_train_full.skip(train_size)



def preprocess_audio(audio, label):
audio = tf.cast(audio, tf.float32)


audio = audio[:16000]
zero_padding = tf.zeros([16000 - tf.shape(audio)[0]], dtype=tf.float32)
audio = tf.concat([audio, zero_padding], 0)

spectrogram = tf.signal.stft(audio, frame_length=255, frame_step=128)
spectrogram = tf.abs(spectrogram)
spectrogram = tf.expand_dims(spectrogram, -1)

return spectrogram, label


AUTOTUNE = tf.data.AUTOTUNE
batch_size = 32

ds_train = ds_train.map(preprocess_audio, num_parallel_calls=AUTOTUNE)
ds_train = ds_train.batch(batch_size).cache().prefetch(AUTOTUNE)

ds_test = ds_test.map(preprocess_audio, num_parallel_calls=AUTOTUNE)
ds_test = ds_test.batch(batch_size).cache().prefetch(AUTOTUNE)


model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(124, 129, 1)), # STFT sonrası approx. shape
tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D((2, 2)),
tf.keras.layers.Dropout(0.25),
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(num_classes, activation='softmax')
])

model.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy']
)

model.summary()


epochs = 5
model.fit(ds_train, validation_data=ds_test, epochs=epochs)


model.save("spoken_digit_model.keras")
print("Model kaydedildi: spoken_digit_model.keras")



def predict_wav(model, wav_file_path, commands):
audio_binary = tf.io.read_file(wav_file_path)
audio, _ = tf.audio.decode_wav(audio_binary)
audio = tf.squeeze(audio, axis=-1)


if tf.shape(audio)[0] > 16000:
audio = audio[:16000]
elif tf.shape(audio)[0] < 16000:
padding = tf.zeros([16000 - tf.shape(audio)[0]], dtype=tf.float32)
audio = tf.concat([audio, padding], 0)

spectrogram = tf.signal.stft(audio, frame_length=255, frame_step=128)
spectrogram = tf.abs(spectrogram)
spectrogram = spectrogram[tf.newaxis, ..., tf.newaxis]

prediction = model.predict(spectrogram)
predicted_id = np.argmax(prediction[0])
return commands[predicted_id], prediction[0][predicted_id]



wav_file = "Kayit.wav"
predicted_command, confidence = predict_wav(model, wav_file, commands)
print(f"Tahmin: {predicted_command}, Güven: {confidence:.4f}")


I tried restarting to rule out possible Windows errors and ran it with administrator privileges, but I couldn't solve this error. I also tried forcing it to run on the CPU, but it still ran on the GPU. I tested another one of my TensorFlow projects, and it ran without any issues, but for some reason, I can't figure this one out.

Continue reading...