ffmpeg -i input.mp4 -ar 16000 -ac 1 output.wav

pip install setuptools
pip install requests
pip install websocket-client

from huaweicloud_sis.client.flash_lasr_client import FlashLasrClient
from huaweicloud_sis.bean.flash_lasr_request import FlashLasrRequest
from huaweicloud_sis.exception.exceptions import ClientException
from huaweicloud_sis.exception.exceptions import ServerException
from huaweicloud_sis.bean.sis_config import SisConfig
import json

config = SisConfig()
config.set_connect_timeout(50)
config.set_read_timeout(50)
client = FlashLasrClient(ak=ak, sk=sk, region=region, project_id=project_id, sis_config=config)

asr_request = FlashLasrRequest()
asr_request.set_obs_bucket_name(obs_bucket_name) # 设置存放音频的桶名，必选
asr_request.set_obs_object_key(obs_object_key) # 设置OBS桶中的对象的键值，必选
asr_request.set_audio_format(audio_format) # 音频格式，必选
asr_request.set_property(property) # property，比如：chinese_16k_conversation
asr_request.set_add_punc('yes')
asr_request.set_digit_norm('no')
asr_request.set_need_word_info('yes')
asr_request.set_first_channel_only('yes')

"word_info": [
 {
 "start_time": 590,
 "word": "哎",
 "end_time": 630
 },
 {
 "start_time": 830,
 "word": "大",
 "end_time": 870
 },
 {
 "start_time": 950,
 "word": "家",
 "end_time": 990
 },
 {
 "start_time": 1110,
 "word": "好",
 "end_time": 1150
 },
]

result = client.get_flash_lasr_result(asr_request)

"result": {
 "score": 0.9358551502227783,
 "word_info": [
 {
 "start_time": 590,
 "word": "哎",
 "end_time": 630
 },
 {
 "start_time": 830,
 "word": "大",
 "end_time": 870
 },
 {
 "start_time": 950,
 "word": "家",
 "end_time": 990
 },
 {
 "start_time": 1110,
 "word": "好",
 "end_time": 1150
 },
 {
 "start_time": 1750,
 "word": "我",
 "end_time": 1790
 },
 {
 "start_time": 1910,
 "word": "是",
 "end_time": 1950
 },
 {
 "start_time": 2070,
 "word": "你",
 "end_time": 2110
 },
 {
 "start_time": 2190,
 "word": "们",
 "end_time": 2230
 },
 {
 "start_time": 2350,
 "word": "的",
 "end_time": 2390
 },
 {
 "start_time": 2870,
 "word": "音",
 "end_time": 2910
 },
 {
 "start_time": 3030,
 "word": "乐",
 "end_time": 3070
 },
 {
 "start_time": 3190,
 "word": "老",
 "end_time": 3230
 },
 {
 "start_time": 3350,
 "word": "师",
 "end_time": 3390
 },
 {
 "start_time": 3590,
 "word": "康",
 "end_time": 3630
 },
 {
 "start_time": 3750,
 "word": "老",
 "end_time": 3790
 },
 {
 "start_time": 3950,
 "word": "师",
 "end_time": 3990
 },
 {
 "start_time": 4830,
 "word": "那",
 "end_time": 4870
 },
 {
 "start_time": 4990,
 "word": "么",
 "end_time": 5030
 },
 {
 "start_time": 5350,
 "word": "这",
 "end_time": 5390
 },
 {
 "start_time": 5550,
 "word": "几",
 "end_time": 5590
 },
 {
 "start_time": 5750,
 "word": "系",
 "end_time": 5790
 },
 {
 "start_time": 5870,
 "word": "列",
 "end_time": 5910
 },
 {
 "start_time": 6070,
 "word": "呢",
 "end_time": 6110
 },
 {
 "start_time": 6310,
 "word": "我",
 "end_time": 6350
 },
 {
 "start_time": 6390,
 "word": "们",
 "end_time": 6470
 },
 {
 "start_time": 6510,
 "word": "来",
 "end_time": 6550
 },
 {
 "start_time": 6670,
 "word": "到",
 "end_time": 6710
 },
 {
 "start_time": 6830,
 "word": "了",
 "end_time": 6870
 },
 {
 "start_time": 7430,
 "word": "发",
 "end_time": 7470
 },
 {
 "start_time": 7630,
 "word": "声",
 "end_time": 7670
 },
 {
 "start_time": 7830,
 "word": "练",
 "end_time": 7870
 },
 {
 "start_time": 8030,
 "word": "习",
 "end_time": 8070
 },
 {
 "start_time": 8950,
 "word": "三",
 "end_time": 8990
 },
 {
 "start_time": 9190,
 "word": "十",
 "end_time": 9230
 },
 {
 "start_time": 9350,
 "word": "五",
 "end_time": 9390
 },
 {
 "start_time": 9470,
 "word": "讲",
 "end_time": 9510
 }
 ],
 "text": "哎，大家好，我是你们的音乐老师康老师。那么这几系列呢，我们来到了发声练习三十五讲。"
 },
 "start_time": 510,
 "end_time": 9640
}

def json2srt(json_result):
    results = ""
    count = 1
 max_word_in_line = 15
 min_word_in_line = 3
 punc = ["。", "？", "！", "，"]
    segments = json_result['flash_result'][0]['sentences']
 for i in range(len(segments)):
 current_result = segments[i]
 current_sentence = current_result["result"]["text"]
 if len(current_result["result"]["word_info"]) > max_word_in_line:
 srt_result = ""
 srt_result_len = 0
 current_segment = ""
 cnt = 0
            start = True
 for i in range(len(current_sentence)):
 if current_sentence[i] not in punc:
 if start:
 start_time = current_result["result"]["word_info"][cnt]['start_time']
                        start = False
 else:
 end_time = current_result["result"]["word_info"][cnt]['end_time']
 current_segment += current_sentence[i]
 srt_result_len += 1
 cnt += 1
 else:
 if srt_result_len < min_word_in_line:
 srt_result += current_segment + current_sentence[i]
 current_segment = ""
 else:
 srt_result += current_segment + current_sentence[i]
 current_segment = ""
 start_time = time_format(start_time)
 end_time = time_format(end_time)
 if srt_result[-1] == "，":
 srt_result = srt_result[:-1]
                        results += str(count) + "\n" + start_time + "-->" + end_time + "\n" + srt_result + "\n" + "\n"
                        count += 1
                        start = True
 srt_result = ""
 else:
 start_time = time_format(current_result["start_time"])
 end_time = time_format(current_result["end_time"])
 if current_sentence[-1] == "，":
 current_sentence = current_sentence[:-1]
            results += str(count) + "\n" + start_time + "-->" + end_time + "\n" + current_sentence + "\n" + "\n"
            count += 1
 return results

ffmpeg -i input.mp4 -vf subtitles=subtitle.srt output_srt.mp4