本文摘抄自 FunASR 项目的官方 Markdown 文件
FunASR 的快速上手
下面为快速上手教程，测试音频（中文，英文）
可执行命令行
在命令行终端执行：
funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=vad_example.wav注：支持单条音频文件识别，也支持文件列表，列表为kaldi风格wav.scp：wav_id wav_path
python示例
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)注：model_hub：表示模型仓库，ms为选择modelscope下载，hf为选择huggingface下载。
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)注：chunk_size为流式延时配置，[0,10,5]表示上屏实时出字粒度为10*60=600ms，未来信息为5*60=300ms。每次推理输入为600ms（采样点数为16000*0.6=960），输出为对应文字，最后一个语音片段输入需要设置is_final=True来强制输出最后一个字。
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)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)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)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)更多详细用法（示例）