update code

shixian.shi

2024-03-08 7498bd7388afdde8d5e6f8a4cb6aeb8be8ac60fa

 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
@@ -38,7 +33,6 @@
    
    def __init__(
        self,
        # token_list: Union[Tuple[str, ...], List[str]],
        specaug: Optional[str] = None,
        specaug_conf: Optional[Dict] = None,
        normalize: str = None,
@@ -160,8 +154,8 @@
        self.predictor_bias = predictor_bias
        self.sampling_ratio = sampling_ratio
        self.criterion_pre = mae_loss(normalize_length=length_normalized_loss)
        # self.step_cur = 0
        #


        self.share_embedding = share_embedding
        if self.share_embedding:
            self.decoder.embed = None
@@ -169,6 +163,7 @@
        self.use_1st_decoder_loss = use_1st_decoder_loss
        self.length_normalized_loss = length_normalized_loss
        self.beam_search = None
        self.error_calculator = None
    
    def forward(
        self,
@@ -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,
@@ -456,11 +451,13 @@
            self.nbest = kwargs.get("nbest", 1)
        
        meta_data = {}
        if isinstance(data_in, torch.Tensor): # fbank
        if isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank": # fbank
            speech, speech_lengths = data_in, data_lengths
            if len(speech.shape) < 3:
                speech = speech[None, :, :]
            if speech_lengths is None:
            if speech_lengths is not None:
                speech_lengths = speech_lengths.squeeze(-1)
            else:
                speech_lengths = speech.shape[1]
        else:
            # extract fbank feats
@@ -496,6 +493,8 @@
        b, n, d = decoder_out.size()
        if isinstance(key[0], (list, tuple)):
            key = key[0]
        if len(key) < b:
            key = key*b
        for i in range(b):
            x = encoder_out[i, :encoder_out_lens[i], :]
            am_scores = decoder_out[i, :pre_token_length[i], :]
@@ -517,9 +516,10 @@
                nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
            for nbest_idx, hyp in enumerate(nbest_hyps):
                ibest_writer = None
                if ibest_writer is None and kwargs.get("output_dir") is not None:
                    writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = writer[f"{nbest_idx+1}best_recog"]
                if kwargs.get("output_dir") is not None:
                    if not hasattr(self, "writer"):
                        self.writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = self.writer[f"{nbest_idx+1}best_recog"]
                # remove sos/eos and get results
                last_pos = -1
                if isinstance(hyp.yseq, list):
@@ -533,13 +533,12 @@
                if tokenizer is not None:
                    # Change integer-ids to tokens
                    token = tokenizer.ids2tokens(token_int)
                    text = tokenizer.tokens2text(token)
                    
                    text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                    text_postprocessed = tokenizer.tokens2text(token)
                    if not hasattr(tokenizer, "bpemodel"):
                        text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                    
                    result_i = {"key": key[i], "text": text_postprocessed}

                    
                    if ibest_writer is not None:
                        ibest_writer["token"][key[i]] = " ".join(token)
                        # ibest_writer["text"][key[i]] = text