damo asr funasr1.0

README.md

@@ -69,7 +69,7 @@ pip install torch numpy scipy tensorboard librosa==0.9.2 numba==0.56.4 pytorch-l
 If you need Chinese ASR (supported by FunASR), install:
 
 ```bash
-pip install modelscope torchaudio sentencepiece funasr
+pip install modelscope torchaudio sentencepiece funasr>=1.0.0
 ```
 
 #### FFmpeg

requirements.txt

@@ -8,7 +8,7 @@ gradio==3.14.0
 ffmpeg-python
 onnxruntime
 tqdm
-funasr
+funasr>=1.0.0
 cn2an
 pypinyin
 pyopenjtalk

tools/damo_asr/cmd-asr.py

@@ -1,9 +1,11 @@
 # -*- coding:utf-8 -*-
 
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
 import sys,os,traceback
+
+from funasr import AutoModel
+
 dir=sys.argv[1]
+
 # opt_name=dir.split("\\")[-1].split("/")[-1]
 opt_name=os.path.basename(dir)
 
@@ -13,17 +15,19 @@ path_punc='tools/damo_asr/models/punc_ct-transformer_zh-cn-common-vocab272727-py
 path_asr=path_asr if os.path.exists(path_asr)else "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
 path_vad=path_vad if os.path.exists(path_vad)else "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
 path_punc=path_punc if os.path.exists(path_punc)else "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-inference_pipeline = pipeline(
-    task=Tasks.auto_speech_recognition,
-    model=path_asr,
-    vad_model=path_vad,
-    punc_model=path_punc,
-)
+
+model = AutoModel(model=path_asr, model_revision="v2.0.3",
+                  vad_model=path_vad,
+                  vad_model_revision="v2.0.2",
+                  punc_model=path_punc,
+                  punc_model_revision="v2.0.3",
+                  )
+
 
 opt=[]
 for name in os.listdir(dir):
     try:
-        text = inference_pipeline(audio_in="%s/%s"%(dir,name))["text"]
+        text = model.generate(input="%s/%s"%(dir,name))[0]["text"]
         opt.append("%s/%s|%s|ZH|%s"%(dir,name,opt_name,text))
     except:
         print(traceback.format_exc())
@@ -31,4 +35,3 @@ for name in os.listdir(dir):
 opt_dir="output/asr_opt"
 os.makedirs(opt_dir,exist_ok=True)
 with open("%s/%s.list"%(opt_dir,opt_name),"w",encoding="utf-8")as f:f.write("\n".join(opt))
-