fix func Forward

雾聪

2024-03-29 9ba0dbd98bf69c830dfcfde8f109a400cb65e4e5

 funasr/models/monotonic_aligner/model.py

@@ -1,22 +1,27 @@
#!/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
import copy
import torch
from torch.cuda.amp import autocast
from typing import Union, Dict, List, Tuple, Optional

from funasr.register import tables
from funasr.models.ctc.ctc import CTC
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.models.paraformer.cif_predictor import mae_loss
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
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
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.load_utils import load_audio_text_image_video, extract_fbank


@tables.register("model_classes", "monotonicaligner")
@tables.register("model_classes", "MonotonicAligner")
class MonotonicAligner(torch.nn.Module):
    """
    Author: Speech Lab of DAMO Academy, Alibaba Group
@@ -41,15 +46,15 @@
        super().__init__()

        if specaug is not None:
            specaug_class = tables.specaug_classes.get(specaug.lower())
            specaug_class = tables.specaug_classes.get(specaug)
            specaug = specaug_class(**specaug_conf)
        if normalize is not None:
            normalize_class = tables.normalize_classes.get(normalize.lower())
            normalize_class = tables.normalize_classes.get(normalize)
            normalize = normalize_class(**normalize_conf)
        encoder_class = tables.encoder_classes.get(encoder.lower())
        encoder_class = tables.encoder_classes.get(encoder)
        encoder = encoder_class(input_size=input_size, **encoder_conf)
        encoder_output_size = encoder.output_size()
        predictor_class = tables.predictor_classes.get(predictor.lower())
        predictor_class = tables.predictor_classes.get(predictor)
        predictor = predictor_class(**predictor_conf)
        self.specaug = specaug
        self.normalize = normalize
@@ -143,7 +148,7 @@

        return encoder_out, encoder_out_lens
    
    def generate(self,
    def inference(self,
             data_in,
             data_lengths=None,
             key: list=None,
@@ -166,7 +171,8 @@
        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)
@@ -177,9 +183,11 @@
        
        results = []
        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["tp_res"]
        if kwargs.get("output_dir") is not None:
            if not hasattr(self, "writer"):
                self.writer = DatadirWriter(kwargs.get("output_dir"))
            ibest_writer = self.writer["tp_res"]

        for i, (us_alpha, us_peak, token_int) in enumerate(zip(us_alphas, us_peaks, text_token_int_list)):
            token = tokenizer.ids2tokens(token_int)
            timestamp_str, timestamp = ts_prediction_lfr6_standard(us_alpha[:encoder_out_lens[i] * 3],