From 54931dd4e1a099d7d6f144c4e12e5453deb3aa26 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 28 六月 2023 10:41:57 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main
---
funasr/models/e2e_tp.py | 42 ++++++++++++++++++++++++++++++------------
1 files changed, 30 insertions(+), 12 deletions(-)
diff --git a/funasr/models/e2e_tp.py b/funasr/models/e2e_tp.py
index 8808008..33948f9 100644
--- a/funasr/models/e2e_tp.py
+++ b/funasr/models/e2e_tp.py
@@ -17,9 +17,8 @@
from funasr.modules.add_sos_eos import add_sos_eos
from funasr.modules.nets_utils import make_pad_mask, pad_list
from funasr.torch_utils.device_funcs import force_gatherable
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
from funasr.models.predictor.cif import CifPredictorV3
-
if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
from torch.cuda.amp import autocast
@@ -30,9 +29,9 @@
yield
-class TimestampPredictor(AbsESPnetModel):
+class TimestampPredictor(FunASRModel):
"""
- Author: Speech Lab, Alibaba Group, China
+ Author: Speech Lab of DAMO Academy, Alibaba Group
"""
def __init__(
@@ -41,6 +40,7 @@
encoder: AbsEncoder,
predictor: CifPredictorV3,
predictor_bias: int = 0,
+ token_list=None,
):
assert check_argument_types()
@@ -54,7 +54,8 @@
self.predictor = predictor
self.predictor_bias = predictor_bias
self.criterion_pre = mae_loss()
-
+ self.token_list = token_list
+
def forward(
self,
speech: torch.Tensor,
@@ -63,7 +64,6 @@
text_lengths: torch.Tensor,
) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
"""Frontend + Encoder + Decoder + Calc loss
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -111,7 +111,6 @@
self, speech: torch.Tensor, speech_lengths: torch.Tensor
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Frontend + Encoder. Note that this method is used by asr_inference.py
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -126,7 +125,7 @@
encoder_out, encoder_out_lens, _ = self.encoder(feats, feats_lengths)
return encoder_out, encoder_out_lens
-
+
def _extract_feats(
self, speech: torch.Tensor, speech_lengths: torch.Tensor
) -> Tuple[torch.Tensor, torch.Tensor]:
@@ -148,7 +147,26 @@
def calc_predictor_timestamp(self, encoder_out, encoder_out_lens, token_num):
encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
encoder_out.device)
- ds_alphas, ds_cif_peak, us_alphas, us_cif_peak = self.predictor.get_upsample_timestamp(encoder_out,
- encoder_out_mask,
- token_num)
- return ds_alphas, ds_cif_peak, us_alphas, us_cif_peak
+ ds_alphas, ds_cif_peak, us_alphas, us_peaks = self.predictor.get_upsample_timestamp(encoder_out,
+ encoder_out_mask,
+ token_num)
+ return ds_alphas, ds_cif_peak, us_alphas, us_peaks
+
+ def collect_feats(
+ self,
+ speech: torch.Tensor,
+ speech_lengths: torch.Tensor,
+ text: torch.Tensor,
+ text_lengths: torch.Tensor,
+ ) -> Dict[str, torch.Tensor]:
+ if self.extract_feats_in_collect_stats:
+ feats, feats_lengths = self._extract_feats(speech, speech_lengths)
+ else:
+ # Generate dummy stats if extract_feats_in_collect_stats is False
+ logging.warning(
+ "Generating dummy stats for feats and feats_lengths, "
+ "because encoder_conf.extract_feats_in_collect_stats is "
+ f"{self.extract_feats_in_collect_stats}"
+ )
+ feats, feats_lengths = speech, speech_lengths
+ return {"feats": feats, "feats_lengths": feats_lengths}
--
Gitblit v1.9.1