文章目录
功能概要
采用阿里通义实验室发布的开源项目 FunAudioLLM，甚至有识别方言的选项。基于FunAudioLLM工具库部署Fun-ASR-Nano-2512语音识别模型，实现以下功能：
（1）GPU运算
（2）利用VAD自动判断何时断句进行检测
（3）能够手动选择收音设备
（4）将检测结果显示在GUI中，若停顿超过固定时间则文字换行
基本环境配置
windows环境下安装anaconda创建虚拟环境，基于python使用pycharm调试，详情参考的我的文章：
（1）安装最新版的anaconda和pycharm
最好都用最新版的，互相兼容。
anaconda下载地址：
https://www.anaconda.com/download
pycharm下载地址：社区版和收费版合并了，收费到期自动变成社区版
https://www.jetbrains.com/pycharm/download/
（2）base环境下安装mamba
bash
conda update conda
conda install mamba -n base -c conda-forge
mamba --version # 验证安装成功（3）创建虚拟环境并安装依赖包
其中ffmpeg 需要收到下载windows版本单独安装，conda和pip安装都不好使。https://www.ffmpeg.org/download.html
bash
mamba create -n llm_api python=3.11 -y
mamba activate llm_api
# PyTorch GPU（CUDA 12.4）
mamba install pytorch torchvision torchaudio pytorch-cuda=12.4 -c pytorch -c nvidia -y
# Transformers生态
mamba install transformers accelerate peft datasets scikit-learn -c conda-forge -y
# bitsandbytes（必须用pip，conda版容易编译失败）
pip install bitsandbytes -i https://pypi.tuna.tsinghua.edu.cn/simple
# Web服务 + 通信 + 工具
pip install fastapi uvicorn pyserial requests matplotlib ollama -i https://pypi.tuna.tsinghua.edu.cn/simple
# 语音识别（Whisper 依赖 torchaudio 已装）
pip install openai-whisper -i https://pypi.tuna.tsinghua.edu.cn/simple
# 我选择的是国产的Fun-ASR模型
pip install funasr[all] -i https://pypi.tuna.tsinghua.edu.cn/simple
# 若报错清理缓存后再试即可
mamba install -c ffmpeg -y
# 安装 modelscope 库
pip install modelscope
# 下载 Fun-ASR-Nano-2512 模型，默认下载到 C:\Users\Administrator\.cache\modelscope\models\FunAudioLLM--Fun-ASR-Nano-2512
modelscope download --model FunAudioLLM/Fun-ASR-Nano-2512Fun-ASR-Nano-2512 模型下载
通过modelscope下载，下载后将模型文件转移至工程目录下，目录结构按照以下配置：
E:\Project\Fun_ASR\models\FunAudioLLM--Fun-ASR-Nano-2512
模型官方页面：https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512
modelscope下载代码：
bash
modelscope download --model FunAudioLLM/Fun-ASR-Nano-2512完整可运行代码
记得运行过程中要根据列出的音频设备信息输入数字指定收音设备
python
import os
import time
import threading
import queue
import tempfile
import soundfile as sf
import pyaudio
import numpy as np
import tkinter as tk
from tkinter import scrolledtext
from funasr import AutoModel
# ==================== 用户配置区域 ====================
# 模型文件夹E:\Project\Fun_AS这个目录再往下就是models文件夹
os.environ["MODELSCOPE_CACHE"] = r"E:\Project\Fun_ASR"
# 指定热点词汇以校准常用词汇的语音识别
HOTWORDS = "王桑:200 吴桑:200 小傻瓜 龟儿子:90 中国人 地球人"
CONFIDENCE_THRESHOLD = 0.2 # 置信度控制
SILENCE_TIMEOUT_GUI = 3.0 # 换行时间间隔
VAD_FRAME_DURATION = 0.3 # vad每0.3秒自动判断是否有语音
SILENCE_DURATION = 0.6 # 静音0.3秒视为一段话结束
# ==================== 音频参数 ====================
CHUNK = int(16000 * 0.1)
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
VAD_FRAME_SAMPLES = int(RATE * VAD_FRAME_DURATION)
SILENCE_FRAMES = int(SILENCE_DURATION / VAD_FRAME_DURATION)
# ==================== 全局变量 ====================
result_queue = queue.Queue()
is_running = True
MIC_DEVICE_INDEX = None
# ==================== 加载模型 ====================
def load_models():
print("正在加载 ASR 模型...")
asr_model = AutoModel(
model="FunAudioLLM/Fun-ASR-Nano-2512",
device="cuda:0",
trust_remote_code=True,
disable_update=True,
)
print("ASR 模型加载完成！")
print("正在加载 VAD 模型...")
vad_model = AutoModel(
model="fsmn-vad",
device="cuda:0",
trust_remote_code=True,
disable_update=True,
)
print("VAD 模型加载完成！")
return asr_model, vad_model
# ==================== 主线程 ====================
def audio_and_asr_worker(asr_model, vad_model, mic_index):
global is_running
p = pyaudio.PyAudio()
stream = p.open(
format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
input_device_index=mic_index,
frames_per_buffer=CHUNK,
)
print(f"🎤 音频线程启动，VAD帧长: {VAD_FRAME_DURATION}s, 静音阈值: {SILENCE_DURATION}s")
speech_buffer = b''
is_speaking = False
silence_counter = 0
frame_buffer = b''
while is_running:
try:
data = stream.read(CHUNK, exception_on_overflow=False)
frame_buffer += data
if len(frame_buffer) >= VAD_FRAME_SAMPLES * 2:
vad_data = frame_buffer[:VAD_FRAME_SAMPLES * 2]
frame_buffer = frame_buffer[VAD_FRAME_SAMPLES * 2:]
# VAD 检测（保存为临时文件）
audio_int16 = np.frombuffer(vad_data, dtype=np.int16)
audio_float = audio_int16.astype(np.float32) / 32768.0
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
tmp_path = tmp.name
sf.write(tmp_path, audio_float, RATE)
try:
vad_res = vad_model.generate(input=[tmp_path], batch_size=1, disable_progress=True)
has_speech = False
if vad_res and len(vad_res) > 0:
for item in vad_res:
if 'value' in item and item['value']:
has_speech = True
break
except Exception as e:
print(f"VAD 异常: {e}")
has_speech = False
finally:
try:
os.unlink(tmp_path)
except:
pass
# ---------- 状态机 ----------
if has_speech:
silence_counter = 0
if not is_speaking:
is_speaking = True
speech_buffer = b''
print("🔊 [语音开始]")
speech_buffer += vad_data
else:
if is_speaking:
silence_counter += 1
speech_buffer += vad_data
if silence_counter >= SILENCE_FRAMES:
is_speaking = False
speech_len = len(speech_buffer)
print(f"🔇 [语音结束]，累积 {speech_len} bytes ({speech_len / (RATE * 2):.2f} 秒)")
if speech_buffer:
# ===== 修复：增强 ASR 调用日志 =====
print("📤 [1] 开始转换为 float32...")
audio_int16_full = np.frombuffer(speech_buffer, dtype=np.int16)
audio_float_full = audio_int16_full.astype(np.float32) / 32768.0
print(f"📤 [2] 转换完成，shape: {audio_float_full.shape}")
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
tmp_path = tmp.name
sf.write(tmp_path, audio_float_full, RATE)
print(f"📤 [3] 临时文件已保存: {tmp_path}")
try:
print("📤 [4] 调用 ASR 识别...")
res = asr_model.generate(
input=[tmp_path],
batch_size=1,
disable_progress=True,
hotword=HOTWORDS,
language="zh",
use_itn=True,
output_timestamp=True,
beam_size=5,
decoding_ctc_weight=0.3,
)
print(f"📤 [5] ASR 返回: {res}")
if res and len(res) > 0:
timestamps = res[0].get("timestamps", [])
if timestamps:
filtered_tokens = []
for token_info in timestamps:
score = token_info.get("score", 0)
token = token_info.get("token", "")
if score >= CONFIDENCE_THRESHOLD:
filtered_tokens.append(token)
filtered_text = ''.join(filtered_tokens).strip()
if filtered_text:
print(f"✅ 识别结果: {filtered_text}")
result_queue.put(filtered_text)
else:
print("⚠️ 过滤后为空")
else:
text = res[0].get("text", "").strip()
if text:
print(f"✅ 识别结果: {text}")
result_queue.put(text)
else:
print("⚠️ text 字段为空")
else:
print("⚠️ ASR 返回空或格式异常")
except Exception as e:
print(f"❌ ASR 识别异常: {e}")
import traceback
traceback.print_exc()
finally:
try:
os.unlink(tmp_path)
print("📤 [6] 临时文件已删除")
except Exception as e:
print(f"删除临时文件失败: {e}")
speech_buffer = b''
except Exception as e:
print(f"❌ 主循环异常: {e}")
import traceback
traceback.print_exc()
break
stream.stop_stream()
stream.close()
p.terminate()
print("音频线程已停止。")
# ==================== GUI ====================
class VoiceApp:
def __init__(self, root):
self.root = root
root.title("🎤 王桑的实时语音识别 (调试版) - FunASR")
root.geometry("800x400")
self.text_area = scrolledtext.ScrolledText(
root, wrap=tk.WORD, font=("微软雅黑", 14),
bg="#f0f0f0", fg="#333333"
)
self.text_area.pack(padx=10, pady=10, fill=tk.BOTH, expand=True)
self.text_area.insert(tk.END, "等待语音输入...")
self.text_area.see(tk.END)
status_text = f"🔊 调试模式 | 阈值: {CONFIDENCE_THRESHOLD}"
self.status = tk.Label(root, text=status_text, font=("微软雅黑", 9), fg="#555")
self.status.pack(pady=(0, 10))
self.last_display_time = None
self.root.protocol("WM_DELETE_WINDOW", self.on_closing)
self.root.after(100, self.update_text)
def update_text(self):
now = time.time()
texts = []
while not result_queue.empty():
try:
texts.append(result_queue.get_nowait())
except queue.Empty:
break
if texts:
if self.last_display_time is None or (now - self.last_display_time) > SILENCE_TIMEOUT_GUI:
self.text_area.insert(tk.END, "\n" + texts[0])
else:
self.text_area.insert(tk.END, " " + texts[0])
for t in texts[1:]:
self.text_area.insert(tk.END, " " + t)
self.text_area.see(tk.END)
self.last_display_time = now
self.root.after(100, self.update_text)
def on_closing(self):
global is_running
is_running = False
self.root.destroy()
# ==================== 设备选择 ====================
def select_microphone():
p = pyaudio.PyAudio()
print("\n===== 可用的录音设备列表 =====")
input_devices = []
for i in range(p.get_device_count()):
info = p.get_device_info_by_index(i)
if info['maxInputChannels'] > 0:
input_devices.append((i, info['name']))
print(f" [{i}] {info['name']} (输入通道: {info['maxInputChannels']})")
p.terminate()
if not input_devices:
print("❌ 未找到任何录音设备")
exit(1)
while True:
try:
choice = input("\n请选择设备编号: ")
idx = int(choice)
if any(idx == dev[0] for dev in input_devices):
print(f"✅ 已选择: {[dev[1] for dev in input_devices if dev[0] == idx][0]}")
return idx
else:
print("⚠️ 编号无效")
except ValueError:
print("⚠️ 请输入数字")
# ==================== 主程序 ====================
if __name__ == "__main__":
mic_idx = select_microphone()
asr_model, vad_model = load_models()
asr_thread = threading.Thread(target=audio_and_asr_worker, args=(asr_model, vad_model, mic_idx), daemon=True)
asr_thread.start()
root = tk.Tk()
app = VoiceApp(root)
root.mainloop()
print("程序退出。")语音识别效果视频
语音识别效果视频