atsr

语帆

2024-03-01 de21c10a2e8a7f93719902708a5ca7970d9e3f00

atsr

 funasr/models/lcbnet/model.py

@@ -426,12 +426,11 @@
                                                            tokenizer=tokenizer)
            time2 = time.perf_counter()
            meta_data["load_data"] = f"{time2 - time1:0.3f}"
            pdb.set_trace()
            audio_sample_list = sample_list[0]
            if len(sample_list) >1:
                ocr_sample_list = sample_list[1]
            else:
                ocr_sample_list = [294, 0]
                ocr_sample_list = [[294, 0]]
            speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
                                                   frontend=frontend)
            time3 = time.perf_counter()