|
|
|
import wave |
|
from pathlib import Path |
|
from typing import Tuple |
|
import sys |
|
import numpy as np |
|
import sherpa_onnx |
|
|
|
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() |
|
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/encoder.onnx", |
|
decoder="am/decoder.onnx", |
|
joiner="am/joiner.onnx", |
|
tokens="lang/tokens.txt", |
|
num_threads=4, |
|
sample_rate=16000, |
|
decoding_method="greedy_search") |
|
|
|
samples, sample_rate = read_wave("test.wav") |
|
s = recognizer.create_stream() |
|
s.accept_waveform(sample_rate, samples) |
|
recognizer.decode_stream(s) |
|
print (s.result.text) |
|
|
|
if __name__ == "__main__": |
|
main() |
|
|
|
|
