语音录入和DeepSeek大模型的调研笔记

整个的流程

1. 使用麦克风录制音频文件
2. 把录制生成的音频文件上传给SenseVoice，实现音频转文本的功能
3. 把SenseVoice返回的结果文本作为输入给DeepSeek
4. 输出DeepSeek的结果

DeepSeek的调用

DeepSeek如果调用官方在线的API，其实比较简单，用官方的示例即可完成最基本的交互，把代码中的api_key换成自己的key就可以了。

aiClient = OpenAI(api_key="这里换成自己的key", base_url="https://api.deepseek.com")

response = aiClient.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "你是一个精通百科知识的知识官。"},
        {"role": "user", "content": inputText},
    ],
    stream=False
)

print(response.choices[0].message.content)

SenseVoice的部署

SenseVoice的部署我是参照下面这篇文章的：
https://blog.csdn.net/weixin_49735366/article/details/145430989
部署完成后可以通过http://127.0.0.1:7860/ 去访问，在网页上直接能完成音频文件和麦克风音频的转换。

页面上有对这个模型的介绍，这属于SenseVoice-Small模型，推荐30秒内的音频数据。

API调用

网页的底部，有个【通过API使用】的链接，点了以后提供了简单的API调用的示例：

from gradio_client import Client, handle_file

client = Client("http://127.0.0.1:7860/")
result = client.predict(
		input_wav=handle_file('https://github.com/gradio-app/gradio/raw/main/test/test_files/audio_sample.wav'),
		language="auto",
		api_name="/model_inference"
)
print(result)

麦克风录制

上面的API调用的示例，也是文件上传的方式。所以流程串起来，需要使用麦克风录制音频，然后把音频文件上传。
下面是完整的客户端示例代码：

import io
import time
import wave
import requests
import speech_recognition as sr
from tqdm import tqdm
import re
from gradio_client import Client, handle_file
from openai import OpenAI

class AudioRecorder:
    def __init__(self, rate=16000):
        """初始化录音器，设置采样率"""
        self.rate = rate
        self.recognizer = sr.Recognizer()

    def record(self):
        """录制音频并返回音频数据"""
        with sr.Microphone(sample_rate=self.rate) as source:
            print("请在倒计时结束前说话", flush=True)
            time.sleep(0.1)  # 确保print输出
            start_time = time.time()
            audio = None

            for _ in tqdm(range(20), desc="倒计时", unit="s"):
                try:
                    # 录音，设置超时1秒以便更新进度条
                    audio = self.recognizer.listen(
                        source, timeout=1, phrase_time_limit=15
                    )
                    break  # 录音成功，跳出循环
                except sr.WaitTimeoutError:
                    # 超时未检测到语音
                    if time.time() - start_time > 20:
                        print("未检测到语音输入")
                        break

            if audio is None:
                print("未检测到语音输入")
                return None

        # 返回音频数据
        audio_data = audio.get_wav_data()
        return io.BytesIO(audio_data)

    def save_wav(self, audio_data, filename="temp_output.wav"):
        """将音频数据保存为WAV文件"""
        audio_data.seek(0)
        with wave.open(filename, "wb") as wav_file:
            nchannels = 1
            sampwidth = 2  # 16-bit audio
            framerate = self.rate  # 采样率
            comptype = "NONE"
            compname = "not compressed"
            audio_frames = audio_data.read()

            wav_file.setnchannels(nchannels)
            wav_file.setsampwidth(sampwidth)
            wav_file.setframerate(framerate)
            wav_file.setcomptype(comptype, compname)
            wav_file.writeframes(audio_frames)
        audio_data.seek(0)

    def run(self):
        """运行录音功能并保存音频文件"""
        audio_data = self.record()
        filename = "temp_output.wav"
        if audio_data:
            self.save_wav(audio_data, filename)
        return filename


class SenseVoice:
    def __init__(self, api_url, emo=False):
        """初始化语音识别接口，设置API URL和情感识别开关"""
        self.api_url = api_url
        self.emo = emo

    def _extract_second_bracket_content(self, raw_text):
        """提取文本中第二对尖括号内的内容"""
        match = re.search(r"<[^<>]*><([^<>]*)>", raw_text)
        if match:
            return match.group(1)
        return None

    def _get_speech_text(self, audio_data):
        """将音频数据发送到API并获取识别结果"""
        print("正在进行语音识别")
        files = [("files", audio_data)]
        data = {"keys": "audio1", "lang": "auto"}

        response = requests.post(self.api_url, files=files, data=data)
        if response.status_code == 200:
            result_json = response.json()
            if "result" in result_json and len(result_json["result"]) > 0:
                if self.emo:
                    result = (
                        self._extract_second_bracket_content(
                            result_json["result"][0]["raw_text"]
                        )
                        + "\n"
                        + result_json["result"][0]["text"]
                    )
                    return result
                else:
                    return result_json["result"][0]["text"]
            else:
                return "未识别到有效的文本"
        else:
            return f"请求失败，状态码: {response.status_code}"

    def speech_to_text(self, audio_data):
        """调用API进行语音识别并返回结果"""
        return self._get_speech_text(audio_data)


# 使用示例
if __name__ == "__main__":
    recorder = AudioRecorder()
    audio_data = recorder.run()

    if audio_data:
        client = Client("http://127.0.0.1:7860/")
        inputText = client.predict(
            input_wav=handle_file(audio_data),
            language="zh",
            api_name="/model_inference",
        )
        print(inputText)

        aiClient = OpenAI(
            api_key="这里换成你自己的key", base_url="https://api.deepseek.com"
        )

        response = aiClient.chat.completions.create(
            model="deepseek-chat",
            messages=[
                {"role": "system", "content": "你是一个精通百科知识的知识官。"},
                {"role": "user", "content": inputText},
            ],
            stream=False,
        )

        print(response.choices[0].message.content)

上面的代码，依赖一些库文件，安装对应的库文件即可。

运行效果：