code optimize, model update, scripts

shixian.shi

2024-01-15 97d648c255316ec1fff5d82e46749076faabdd2d

 funasr/models/contextual_paraformer/model.py

@@ -1,42 +1,34 @@
#!/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 os
import re
import time
import torch
import codecs
import logging
import tempfile
import requests
import numpy as np
from typing import Dict, Tuple
from contextlib import contextmanager
from distutils.version import LooseVersion
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
import random
import numpy as np
import time
# from funasr.layers.abs_normalize import AbsNormalize

from funasr.register import tables
from funasr.losses.label_smoothing_loss import (
    LabelSmoothingLoss,  # noqa: H301
)
# from funasr.models.ctc import CTC
# from funasr.models.decoder.abs_decoder import AbsDecoder
# from funasr.models.e2e_asr_common import ErrorCalculator
# from funasr.models.encoder.abs_encoder import AbsEncoder
# from funasr.frontends.abs_frontend import AbsFrontend
# from funasr.models.postencoder.abs_postencoder import AbsPostEncoder
from funasr.models.paraformer.cif_predictor import mae_loss
# from funasr.models.preencoder.abs_preencoder import AbsPreEncoder
# from funasr.models.specaug.abs_specaug import AbsSpecAug
from funasr.utils import postprocess_utils
from funasr.metrics.compute_acc import th_accuracy
from funasr.models.paraformer.model import Paraformer
from funasr.utils.datadir_writer import DatadirWriter
from funasr.models.paraformer.search import Hypothesis
from funasr.train_utils.device_funcs import force_gatherable
from funasr.models.transformer.utils.add_sos_eos import add_sos_eos
from funasr.models.transformer.utils.nets_utils import make_pad_mask, pad_list
from funasr.metrics.compute_acc import th_accuracy
from funasr.train_utils.device_funcs import force_gatherable
# from funasr.models.base_model import FunASRModel
# from funasr.models.paraformer.cif_predictor import CifPredictorV3
from funasr.models.paraformer.search import Hypothesis
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank


if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
@@ -46,14 +38,7 @@
    @contextmanager
    def autocast(enabled=True):
        yield
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter


from funasr.models.paraformer.model import Paraformer

from funasr.register import tables

@tables.register("model_classes", "ContextualParaformer")
class ContextualParaformer(Paraformer):
@@ -316,7 +301,7 @@
        decoder_out = torch.log_softmax(decoder_out, dim=-1)
        return decoder_out, ys_pad_lens
        
    def generate(self,
    def inference(self,
                 data_in,
                 data_lengths=None,
                 key: list = None,
@@ -324,7 +309,6 @@
                 frontend=None,
                 **kwargs,
                 ):
        
        # init beamsearch
        is_use_ctc = kwargs.get("decoding_ctc_weight", 0.0) > 0.00001 and self.ctc != None
        is_use_lm = kwargs.get("lm_weight", 0.0) > 0.00001 and kwargs.get("lm_file", None) is not None