funasr/models/llm_asr/model.py
@@ -168,8 +168,6 @@ text: (Batch, Length) text_lengths: (Batch,) """ # import pdb; # pdb.set_trace() if len(text_lengths.size()) > 1: text_lengths = text_lengths[:, 0] if len(speech_lengths.size()) > 1: @@ -1018,7 +1016,7 @@ for turn_id in range(fbank_beg.shape[1]): fbank_beg_idx = fbank_beg[batch_idx, turn_id].item() if fbank_beg[batch_idx, turn_id] > 0: if fbank_beg_idx > 0: speech_token_len = fake_token_len[batch_idx, turn_id] speech_token = encoder_out[speech_idx, :speech_token_len, :]
