如何在VOSK语音识别中使用Wave文件作为输入？

Question

我有一个项目，需要获得一个录制的文件，然后按代码处理，从文件中提取文本，并将提取的文件与其他文本匹配，并验证它。我的问题是:我不能在代码中使用录制的文件，它也不能读取文件

初始化函数是代码的基础。

确认功能确认匹配的语音和文本。

import argparse
import json
import os
import queue
import random
import sys
from difflib import SequenceMatcher
import numpy as np
import sounddevice as sd
import vosk

q = queue.Queue()

def int_or_str(text):
    """Helper function for argument parsing."""
    try:
        return int(text)
    except ValueError:
        return text


def callback(indata, frames, time, status):
    """This is called (from a separate thread) for each audio block."""
    if status:
        print(status, file=sys.stderr)
    q.put(bytes(indata))



def init():
    parser = argparse.ArgumentParser(add_help=False)
    parser.add_argument(
        '-l', '--list-devices', action='store_true',
        help='show list of audio devices and exit')
    args, remaining = parser.parse_known_args()
    if args.list_devices:
        print(sd.query_devices())
        parser.exit(0)
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter,
        parents=[parser])
    parser.add_argument(
        '-f', '--filename', type=str, metavar='FILENAME',
        help='audio file to store recording to')
    parser.add_argument(
        '-m', '--model', type=str, metavar='MODEL_PATH',
        help='Path to the model')
    parser.add_argument(
        '-d', '--device', type=int_or_str,
        help='input device (numeric ID or substring)')
    parser.add_argument(
        '-r', '--samplerate', type=int, help='sampling rate')
    args = parser.parse_args(remaining)
    try:
        if args.model is None:
            args.model = "model"
        if not os.path.exists(args.model):
            print("Please download a model for your language from https://alphacephei.com/vosk/models")
            print("and unpack as 'model' in the current folder.")
            parser.exit(0)
        if args.samplerate is None:
            device_info = sd.query_devices(args.device, 'input')
            # soundfile expects an int, sounddevice provides a float:
            args.samplerate = int(device_info['default_samplerate'])

        model = vosk.Model(args.model)

        if args.filename:
            dump_fn = open(args.filename, "wb")
        else:
            dump_fn = None

        
    except KeyboardInterrupt:
        print('\nDone')
        parser.exit(0)
    except Exception as e:
        parser.exit(type(e).__name__ + ': ' + str(e))

    return model, args
def verify(random_sentence, model, args):
    num, T_num, F_num, num_word = 0, 0, 0, 1
    with sd.RawInputStream(samplerate=args.samplerate, blocksize=8000, device=args.device, dtype='int16',
                           channels=1, callback=callback):
        rec = vosk.KaldiRecognizer(model, args.samplerate)
        print("{}) ".format(num_word), random_sentence, end='\n')
        print('=' * 30, end='\n')
        run = True
        while run:
            data = q.get()
            if rec.AcceptWaveform(data):
                res = json.loads(rec.FinalResult())
                res['text'] = res['text'].replace('ي', 'ی')             
                if SequenceMatcher(None, random_sentence, res['text']).ratio() > 0.65:                    
                    T_num, num, num_word += 1
                    
                else:
                    F_num, num, num_word += 1
                    
                run = False

    print('=' * 30)
    print('True Cases : {}\n False Cases : {}'.format(T_num, F_num))


if __name__ == "__main__":
    model, args = init()
    verify(random_sentences, model, args)

Answer 1

我一直在做一个类似的项目。我修改了the code from VOSK Git repo并编写了以下函数，该函数接受文件名/路径作为输入，并输出捕获的文本。有时，当音频文件中有很长的停顿(~秒)时，返回的文本会是一个空字符串。为了解决这个问题，我不得不编写额外的代码来挑选出捕获的最长字符串。我可以凑合着用这个方法。

def get_text_from_voice(filename):

    if not os.path.exists("model"):
        print ("Please download the model from https://alphacephei.com/vosk/models and unpack as 'model' in the current folder.")
        exit (1)

    wf = wave.open(filename, "rb")
    if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
        print ("Audio file must be WAV format mono PCM.")
        exit (1)

    model = Model("model")
    rec = KaldiRecognizer(model, wf.getframerate())
    rec.SetWords(True)

    text_lst =[]
    p_text_lst = []
    p_str = []
    len_p_str = []
    while True:
        data = wf.readframes(4000)
        if len(data) == 0:
            break
        if rec.AcceptWaveform(data):
            text_lst.append(rec.Result())
            print(rec.Result())
        else:
            p_text_lst.append(rec.PartialResult())
            print(rec.PartialResult())

    if len(text_lst) !=0:
        jd = json.loads(text_lst[0])
        txt_str = jd["text"]
        
    elif len(p_text_lst) !=0: 
        for i in range(0,len(p_text_lst)):
            temp_txt_dict = json.loads(p_text_lst[i])
            p_str.append(temp_txt_dict['partial'])
       
        len_p_str = [len(p_str[j]) for j in range(0,len(p_str))]
        max_val = max(len_p_str)
        indx = len_p_str.index(max_val)
        txt_str = p_str[indx]
            
    else:
        txt_str =''

    return txt_str

确保正确的模型存在于同一目录中，或者放在模型的路径中。另外，请注意，VOSK只接受wav mono PCM格式的音频文件。