code optimize, model update, scripts

shixian.shi

2024-01-15 97d648c255316ec1fff5d82e46749076faabdd2d

 funasr/models/paraformer/model.py

@@ -1,35 +1,30 @@
import os
import logging
from typing import Union, Dict, List, Tuple, Optional

import torch
import torch.nn as nn
#!/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 time

from funasr.losses.label_smoothing_loss import (
    LabelSmoothingLoss,  # noqa: H301
)

from funasr.models.paraformer.cif_predictor import mae_loss

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.paraformer.search import Hypothesis

import torch
import logging
from torch.cuda.amp import autocast
from typing import Union, Dict, List, Tuple, Optional

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.register import tables
from funasr.models.ctc.ctc import CTC
from funasr.utils import postprocess_utils
from funasr.metrics.compute_acc import th_accuracy
from funasr.utils.datadir_writer import DatadirWriter
from funasr.models.paraformer.search import Hypothesis
from funasr.models.paraformer.cif_predictor import mae_loss
from funasr.train_utils.device_funcs import force_gatherable
from funasr.losses.label_smoothing_loss import LabelSmoothingLoss
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.utils.load_utils import load_audio_text_image_video, extract_fbank


@tables.register("model_classes", "Paraformer")
class Paraformer(nn.Module):
class Paraformer(torch.nn.Module):
    """
    Author: Speech Lab of DAMO Academy, Alibaba Group
    Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
@@ -439,7 +434,7 @@
        #         scorer.to(device=kwargs.get("device", "cpu"), dtype=getattr(torch, kwargs.get("dtype", "float32"))).eval()
        self.beam_search = beam_search
        
    def generate(self,
    def inference(self,
             data_in,
             data_lengths=None,
             key: list=None,