speech-recognition-from-microphone.py 2.1 KB
#!/usr/bin/env python3

# Real-time speech recognition from a microphone with sherpa-onnx Python API
#
# Please refer to
# https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
# to download pre-trained models

import sys

try:
    import sounddevice as sd
except ImportError as e:
    print("Please install sounddevice first. You can use")
    print()
    print("  pip install sounddevice")
    print()
    print("to install it")
    sys.exit(-1)

import sherpa_onnx


def create_recognizer():
    # Please replace the model files if needed.
    # See https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
    # for download links.
    recognizer = sherpa_onnx.OnlineRecognizer(
        tokens="./sherpa-onnx-lstm-en-2023-02-17/tokens.txt",
        encoder="./sherpa-onnx-lstm-en-2023-02-17/encoder-epoch-99-avg-1.onnx",
        decoder="./sherpa-onnx-lstm-en-2023-02-17/decoder-epoch-99-avg-1.onnx",
        joiner="./sherpa-onnx-lstm-en-2023-02-17/joiner-epoch-99-avg-1.onnx",
        num_threads=4,
        sample_rate=16000,
        feature_dim=80,
    )
    return recognizer


def main():
    print("Started! Please speak")
    recognizer = create_recognizer()
    sample_rate = 16000
    samples_per_read = int(0.1 * sample_rate)  # 0.1 second = 100 ms
    last_result = ""
    stream = recognizer.create_stream()
    with sd.InputStream(channels=1, dtype="float32", samplerate=sample_rate) as s:
        while True:
            samples, _ = s.read(samples_per_read)  # a blocking read
            samples = samples.reshape(-1)
            stream.accept_waveform(sample_rate, samples)
            while recognizer.is_ready(stream):
                recognizer.decode_stream(stream)
            result = recognizer.get_result(stream)
            if last_result != result:
                last_result = result
                print(result)


if __name__ == "__main__":
    devices = sd.query_devices()
    print(devices)
    default_input_device_idx = sd.default.device[0]
    print(f'Use default device: {devices[default_input_device_idx]["name"]}')

    try:
        main()
    except KeyboardInterrupt:
        print("\nCaught Ctrl + C. Exiting")