File size: 9,160 Bytes
167f5d0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | import logging
from typing import Union, Dict, List, Tuple, Optional
import time
import torch
import torch.nn as nn
from funasr.models.ctc.ctc import CTC
from funasr.train_utils.device_funcs import force_gatherable
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.paraformer.search import Hypothesis
@tables.register("model_classes", "CTC")
class Transformer(nn.Module):
"""CTC-attention hybrid Encoder-Decoder model"""
def __init__(
self,
specaug: str = None,
specaug_conf: dict = None,
normalize: str = None,
normalize_conf: dict = None,
encoder: str = None,
encoder_conf: dict = None,
ctc_conf: dict = None,
input_size: int = 80,
vocab_size: int = -1,
ignore_id: int = -1,
blank_id: int = 0,
sos: int = 1,
eos: int = 2,
length_normalized_loss: bool = False,
**kwargs,
):
super().__init__()
if specaug is not None:
specaug_class = tables.specaug_classes.get(specaug)
specaug = specaug_class(**specaug_conf)
if normalize is not None:
normalize_class = tables.normalize_classes.get(normalize)
normalize = normalize_class(**normalize_conf)
encoder_class = tables.encoder_classes.get(encoder)
encoder = encoder_class(input_size=input_size, **encoder_conf)
encoder_output_size = encoder.output_size()
if ctc_conf is None:
ctc_conf = {}
ctc = CTC(odim=vocab_size, encoder_output_size=encoder_output_size, **ctc_conf)
self.blank_id = blank_id
self.sos = sos if sos is not None else vocab_size - 1
self.eos = eos if eos is not None else vocab_size - 1
self.vocab_size = vocab_size
self.ignore_id = ignore_id
self.specaug = specaug
self.normalize = normalize
self.encoder = encoder
self.error_calculator = None
self.ctc = ctc
self.length_normalized_loss = length_normalized_loss
def forward(
self,
speech: torch.Tensor,
speech_lengths: torch.Tensor,
text: torch.Tensor,
text_lengths: torch.Tensor,
**kwargs,
) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
"""Encoder + Decoder + Calc loss
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
text: (Batch, Length)
text_lengths: (Batch,)
"""
# import pdb;
# pdb.set_trace()
if len(text_lengths.size()) > 1:
text_lengths = text_lengths[:, 0]
if len(speech_lengths.size()) > 1:
speech_lengths = speech_lengths[:, 0]
batch_size = speech.shape[0]
# 1. Encoder
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
loss_ctc, cer_ctc = None, None
stats = dict()
loss_ctc, cer_ctc = self._calc_ctc_loss(
encoder_out, encoder_out_lens, text, text_lengths
)
loss = loss_ctc
# Collect total loss stats
stats["loss"] = torch.clone(loss.detach())
# force_gatherable: to-device and to-tensor if scalar for DataParallel
if self.length_normalized_loss:
batch_size = int((text_lengths + 1).sum())
loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
return loss, stats, weight
def encode(
self,
speech: torch.Tensor,
speech_lengths: torch.Tensor,
**kwargs,
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Frontend + Encoder. Note that this method is used by asr_inference.py
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
ind: int
"""
# Data augmentation
if self.specaug is not None and self.training:
speech, speech_lengths = self.specaug(speech, speech_lengths)
# Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
if self.normalize is not None:
speech, speech_lengths = self.normalize(speech, speech_lengths)
# Forward encoder
# feats: (Batch, Length, Dim)
# -> encoder_out: (Batch, Length2, Dim2)
encoder_out, encoder_out_lens = self.encoder(speech, speech_lengths)
return encoder_out, encoder_out_lens
def _calc_ctc_loss(
self,
encoder_out: torch.Tensor,
encoder_out_lens: torch.Tensor,
ys_pad: torch.Tensor,
ys_pad_lens: torch.Tensor,
):
# Calc CTC loss
loss_ctc = self.ctc(encoder_out, encoder_out_lens, ys_pad, ys_pad_lens)
# Calc CER using CTC
cer_ctc = None
if not self.training and self.error_calculator is not None:
ys_hat = self.ctc.argmax(encoder_out).data
cer_ctc = self.error_calculator(ys_hat.cpu(), ys_pad.cpu(), is_ctc=True)
return loss_ctc, cer_ctc
def inference(
self,
data_in,
data_lengths=None,
key: list = None,
tokenizer=None,
frontend=None,
**kwargs,
):
if kwargs.get("batch_size", 1) > 1:
raise NotImplementedError("batch decoding is not implemented")
meta_data = {}
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:
speech_lengths = speech.shape[1]
else:
# extract fbank feats
time1 = time.perf_counter()
audio_sample_list = load_audio_text_image_video(
data_in,
fs=frontend.fs,
audio_fs=kwargs.get("fs", 16000),
data_type=kwargs.get("data_type", "sound"),
tokenizer=tokenizer,
)
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
speech, speech_lengths = extract_fbank(
audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=frontend
)
time3 = time.perf_counter()
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 = speech.to(device=kwargs["device"])
speech_lengths = speech_lengths.to(device=kwargs["device"])
# Encoder
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
# c. Passed the encoder result and the beam search
ctc_logits = self.ctc.log_softmax(encoder_out)
results = []
b, n, d = encoder_out.size()
if isinstance(key[0], (list, tuple)):
key = key[0]
if len(key) < b:
key = key * b
for i in range(b):
x = ctc_logits[i, :encoder_out_lens[i], :]
yseq = x.argmax(dim=-1)
yseq = torch.unique_consecutive(yseq, dim=-1)
yseq = torch.tensor([self.sos] + yseq.tolist() + [self.eos], device=yseq.device)
nbest_hyps = [Hypothesis(yseq=yseq)]
for nbest_idx, hyp in enumerate(nbest_hyps):
ibest_writer = None
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):
token_int = hyp.yseq[1:last_pos]
else:
token_int = hyp.yseq[1:last_pos].tolist()
# remove blank symbol id, which is assumed to be 0
token_int = list(
filter(
lambda x: x != self.eos and x != self.sos and x != self.blank_id, token_int
)
)
# Change integer-ids to tokens
token = tokenizer.ids2tokens(token_int)
text = tokenizer.tokens2text(token)
text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
result_i = {"key": key[i], "token": token, "text": text_postprocessed}
results.append(result_i)
if ibest_writer is not None:
ibest_writer["token"][key[i]] = " ".join(token)
ibest_writer["text"][key[i]] = text_postprocessed
return results, meta_data
|