代码:

-- coding:utf-8 --

import argparse import os import traceback from tqdm import tqdm

from funasr import AutoModel

model = AutoModel( model = 'tools/asr/models/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch', vad_model = 'tools/asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch', punc_model = 'tools/asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch', )

def only_asr(input_file): try: text = model.generate(input=input_file)[0]["text"] except: text = '' print(traceback.format_exc()) return text

def execute_asr(input_folder, output_folder, model_size, language): input_file_names = os.listdir(input_folder) input_file_names.sort()

output = []
output_file_name = os.path.basename(input_folder)

for file_name in tqdm(input_file_names):
    try:
        file_path = os.path.join(input_folder, file_name)
        text = model.generate(input=file_path)[0]["text"]
        output.append(f"{file_path}|{output_file_name}|{language.upper()}|{text}")
    except:
        print(traceback.format_exc())

output_folder = output_folder or "output/asr_opt"
os.makedirs(output_folder, exist_ok=True)
output_file_path = os.path.abspath(f'{output_folder}/{output_file_name}.list')

with open(output_file_path, "w", encoding="utf-8") as f:
    f.write("\n".join(output))
    print(f"ASR 任务完成->标注文件路径: {output_file_path}\n")
return output_file_path

if name == 'main': parser = argparse.ArgumentParser() parser.add_argument("-i", "--input_folder", type=str, required=True, help="Path to the folder containing WAV files.") parser.add_argument("-o", "--output_folder", type=str, required=True, help="Output folder to store transcriptions.") parser.add_argument("-s", "--model_size", type=str, default='large', help="Model Size of FunASR is Large") parser.add_argument("-l", "--language", type=str, default='zh', choices=['zh'], help="Language of the audio files.") parser.add_argument("-p", "--precision", type=str, default='float16', choices=['float16','float32'], help="fp16 or fp32")#还没接入

cmd = parser.parse_args()
execute_asr(
    input_folder  = cmd.input_folder,
    output_folder = cmd.output_folder,
    model_size    = cmd.model_size,
    language      = cmd.language,
)

modelscope / FunASR

怎样识别出字词带时间戳的识别结果？是否有代码示例 #1812

-- coding:utf-8 --