decode-onnx.py

#!/usr/bin/env python3
import wave
from pathlib import Path
from typing import Tuple
import sys
import numpy as np
import sherpa_onnx

import sys

def read_wave(wave_filename: str) -> Tuple[np.ndarray, int]:
    with wave.open(wave_filename) as f:
        assert f.getnchannels() == 1, f.getnchannels()
        assert f.getsampwidth() == 2, f.getsampwidth()  # it is in bytes
        num_samples = f.getnframes()
        samples = f.readframes(num_samples)
        samples_int16 = np.frombuffer(samples, dtype=np.int16)
        samples_float32 = samples_int16.astype(np.float32)
        samples_float32 = samples_float32 / 32768
        return samples_float32, f.getframerate()

def main():

    recognizer = sherpa_onnx.OfflineRecognizer.from_transducer(
            encoder="am-onnx/encoder.onnx",
            decoder="am-onnx/decoder.onnx",
            joiner="am-onnx/joiner.onnx",
            tokens="lang/tokens.txt",
            num_threads=0,
            provider='cpu',
            sample_rate=16000,
            dither=3e-5,
            max_active_paths=10,
            decoding_method="modified_beam_search")

    samples, sample_rate = read_wave(sys.argv[1])
    s = recognizer.create_stream()
    s.accept_waveform(sample_rate, samples)
    recognizer.decode_stream(s)
    print ("Text:", s.result.text)
    print ("Tokens:", s.result.tokens)
    print ("Timestamps:", s.result.timestamps)

if __name__ == "__main__":
    main()