kaldi-python-io

import kaldi_io import numpy as np import os # Define a path for the temporary Kaldi archive file temp_ark_path = "temp_matrix.ark" try: # 1. Create a NumPy array (e.g., a feature matrix) # Kaldi typically uses float32 for features feature_matrix = np.array([[1.1, 2.2, 3.3], [4.4, 5.5, 6.6]], dtype=np.float32) print(f"Original matrix:\n{feature_matrix}") # 2. Write the NumPy array to a Kaldi archive file # The library supports writing directly to a file path or file-like object # 'key' is important for Kaldi archives to identify the data with kaldi_io.open_or_fd(temp_ark_path, 'wb') as f: kaldi_io.write_mat(f, feature_matrix, key='utt1_features') print(f"Successfully wrote matrix to '{temp_ark_path}' with key 'utt1_features'.") # 3. Read the matrix back from the Kaldi archive file # kaldi_io.read_mat_s is a generator for multiple matrices in an ark file read_data_generator = kaldi_io.read_mat_s(temp_ark_path) # Since we wrote only one, we expect one (key, matrix) tuple. Get the first. key, loaded_matrix = next(read_data_generator) print(f"\nRead back data:") print(f"Key: {key}") print(f"Matrix:\n{loaded_matrix}") # Verify if the loaded matrix matches the original assert np.allclose(feature_matrix, loaded_matrix) print("\nVerification successful: Loaded matrix matches original.") finally: # Clean up the temporary file if os.path.exists(temp_ark_path): os.remove(temp_ark_path) print(f"Cleaned up temporary file: {temp_ark_path}")