安装步骤
conda create -n funasr python=3.9
conda in
pip install torch==1.13
pip install torchaudio
pip install pyaudio
pip install -U funasr
conda activate funasr
资料
www.modelscope.cn/models/iic/…
demo1直接转音频文件
E:\model\FunAudioLLM\SenseVoiceSmall是从魔塔上下载的文件
如果直接下载的报错就把模型变量换成model_dir = "iic/SenseVoiceSmall"
下载到缓存目录后（路径会打印）剪切到想指定的路径即可，指定的路径写到config.yaml那级
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "E:\model\FunAudioLLM\SenseVoiceSmall"
model = AutoModel(
model=model_dir,
vad_model="fsmn-vad",
vad_kwargs={"max_single_segment_time": 30000},
device="cpu",
)
# en
res = model.generate(
input=f"C:\Users\zxppc\Documents\录音\录音 (3).m4a",
cache={},
language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)
建议成功后再修改
demo2试试转麦克风采集的音频
from funasr import AutoModel
import pyaudio
import numpy as np
import os
# 配置参数
chunk_size = [0, 10, 5] # 600ms
encoder_chunk_look_back = 4
decoder_chunk_look_back = 1
model_dir = "E:\model\FunAudioLLM\SenseVoiceSmall"
model = AutoModel(model=model_dir)
# 麦克风配置
FORMAT = pyaudio.paInt16 # 16-bit int
CHANNELS = 1 # 单声道
RATE = 16000 # 采样率 (与模型一致)
CHUNK_SIZE_MS = 600 # 每个 chunk 600ms
CHUNK_SAMPLES = int(RATE * CHUNK_SIZE_MS / 1000) # 样本数
# 初始化 PyAudio
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK_SAMPLES)
print("🎤 正在监听麦克风，请开始说话...")
# 流式识别缓存
cache = {}
chunk_count = 0
try:
while True:
audio_data = stream.read(CHUNK_SAMPLES, exception_on_overflow=False)
speech_chunk = np.frombuffer(audio_data, dtype=np.int16).astype(np.float32) / 32768.0 # 归一化到 [-1, 1]
# 推理
res = model.generate(
input=speech_chunk,
cache=cache,
is_final=False, # 实时识别一般不设为最终帧
chunk_size=chunk_size,
encoder_chunk_look_back=encoder_chunk_look_back,
decoder_chunk_look_back=decoder_chunk_look_back
)
if res and len(res) > 0:
print("🎙️ 识别结果：", res[0]["text"])
except KeyboardInterrupt:
print("\n🛑 停止录音...")
finally:
stream.stop_stream()
stream.close()
p.terminate()
