FunASR基础语音识别工具包
一、核心功能
- FunASR是一个基础语音识别工具包，提供多种功能，包括语音识别（ASR）、语音端点检测（VAD）、标点恢复、语言模型、说话人验证、说话人分离和多人对话语音识别等。FunASR提供了便捷的脚本和教程，支持预训练好的模型的推理与微调。
代码下载地址：modelscope/FunASR: A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
模型下载地址：funasr/paraformer-zh-streaming · HF Mirror
二、安装教程
pip3 install -U funasr
或者
git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip3 install -e ./pip3 install -U modelscope三、模型仓库
四、上手教程
1.可执行命令行
funasr +model=paraformer-zh +vad_model="fsmn-vad" +punc_model="ct-punc" +input=asr_example_zh.wav
2.非实时语音识别
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",vad_model="fsmn-vad", vad_model_revision="v2.0.4",punc_model="ct-punc-c", punc_model_revision="v2.0.4",# spk_model="cam++", spk_model_revision="v2.0.2",)
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", batch_size_s=300, hotword='魔搭')
print(res)
3.实时语音识别
from funasr import AutoModelchunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attentionmodel = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")import soundfile
import oswav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
chunk_stride = chunk_size[1] * 960 # 600mscache = {}
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]is_final = i == total_chunk_num - 1res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)print(res)
4.语音端点检测（非实时）
from funasr import AutoModelmodel = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
wav_file = f"{model.model_path}/example/asr_example.wav"
res = model.generate(input=wav_file)
print(res)
5.语音端点检测（实时）
from funasr import AutoModelchunk_size = 200 # ms
model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")import soundfilewav_file = f"{model.model_path}/example/vad_example.wav"
speech, sample_rate = soundfile.read(wav_file)
chunk_stride = int(chunk_size * sample_rate / 1000)cache = {}
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]is_final = i == total_chunk_num - 1res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)if len(res[0]["value"]):print(res)
6.标点恢复
from funasr import AutoModelmodel = AutoModel(model="ct-punc", model_revision="v2.0.4")
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
print(res)
7.时间戳预测
from funasr import AutoModelmodel = AutoModel(model="fa-zh", model_revision="v2.0.4")
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
8.情感识别
from funasr import AutoModelmodel = AutoModel(model="emotion2vec_plus_large")wav_file = f"{model.model_path}/example/test.wav"res = model.generate(wav_file, output_dir="./outputs", granularity="utterance", extract_embedding=False)
print(res)