bug fix

examples/industrial_data_pretraining/paraformer/demo.py

@@ -11,6 +11,7 @@ res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/Ma
 print(res)
 
 
+''' can not use currently
 from funasr import AutoFrontend
 
 frontend = AutoFrontend(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.2")
@@ -19,4 +20,5 @@ fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/
 
 for batch_idx, fbank_dict in enumerate(fbanks):
     res = model.generate(**fbank_dict)
-    print(res)
+    print(res)
+'''

funasr/models/bicif_paraformer/model.py

@@ -235,23 +235,23 @@ class BiCifParaformer(Paraformer):
             self.nbest = kwargs.get("nbest", 1)
         
         meta_data = {}
-        if isinstance(data_in, torch.Tensor):  # fbank
-            speech, speech_lengths = data_in, data_lengths
-            if len(speech.shape) < 3:
-                speech = speech[None, :, :]
-            if speech_lengths is None:
-                speech_lengths = speech.shape[1]
-        else:
-            # extract fbank feats
-            time1 = time.perf_counter()
-            audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
-            time2 = time.perf_counter()
-            meta_data["load_data"] = f"{time2 - time1:0.3f}"
-            speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
-                                                   frontend=frontend)
-            time3 = time.perf_counter()
-            meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
-            meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
+        # if isinstance(data_in, torch.Tensor):  # fbank
+        #     speech, speech_lengths = data_in, data_lengths
+        #     if len(speech.shape) < 3:
+        #         speech = speech[None, :, :]
+        #     if speech_lengths is None:
+        #         speech_lengths = speech.shape[1]
+        # else:
+        # extract fbank feats
+        time1 = time.perf_counter()
+        audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
+        time2 = time.perf_counter()
+        meta_data["load_data"] = f"{time2 - time1:0.3f}"
+        speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
+                                                frontend=frontend)
+        time3 = time.perf_counter()
+        meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
+        meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
         
         speech = speech.to(device=kwargs["device"])
         speech_lengths = speech_lengths.to(device=kwargs["device"])