funasr1.0

游雁

2024-01-15 c6361cc2a7e99be802d7d7e81a93e874f0faf5cd

 funasr/models/bicif_paraformer/model.py

@@ -1,14 +1,13 @@
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

import logging
from typing import Dict
from typing import List
from typing import Optional
from typing import Tuple
from typing import Union
import tempfile
import codecs
import requests
import re
import copy
import torch
import torch.nn as nn
@@ -252,7 +251,8 @@
            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.to(device=kwargs["device"]), speech_lengths.to(device=kwargs["device"])
        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])
        
        # Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)