From bc723ea200144bd6fa8a5dff4b9a780feda144fc Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 29 六月 2023 18:55:01 +0800
Subject: [PATCH] dcos
---
funasr/models/e2e_diar_eend_ola.py | 21 ++++++++++++++-------
1 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/funasr/models/e2e_diar_eend_ola.py b/funasr/models/e2e_diar_eend_ola.py
index 79cb614..ae3a436 100644
--- a/funasr/models/e2e_diar_eend_ola.py
+++ b/funasr/models/e2e_diar_eend_ola.py
@@ -9,14 +9,13 @@
import numpy as np
import torch
import torch.nn as nn
-from typeguard import check_argument_types
from funasr.models.frontend.wav_frontend import WavFrontendMel23
from funasr.modules.eend_ola.encoder import EENDOLATransformerEncoder
from funasr.modules.eend_ola.encoder_decoder_attractor import EncoderDecoderAttractor
from funasr.modules.eend_ola.utils.power import generate_mapping_dict
from funasr.torch_utils.device_funcs import force_gatherable
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
pass
@@ -34,7 +33,7 @@
return att
-class DiarEENDOLAModel(AbsESPnetModel):
+class DiarEENDOLAModel(FunASRModel):
"""EEND-OLA diarization model"""
def __init__(
@@ -48,7 +47,6 @@
mapping_dict=None,
**kwargs,
):
- assert check_argument_types()
super().__init__()
self.frontend = frontend
@@ -76,7 +74,7 @@
def forward_post_net(self, logits, ilens):
maxlen = torch.max(ilens).to(torch.int).item()
logits = nn.utils.rnn.pad_sequence(logits, batch_first=True, padding_value=-1)
- logits = nn.utils.rnn.pack_padded_sequence(logits, ilens, batch_first=True, enforce_sorted=False)
+ logits = nn.utils.rnn.pack_padded_sequence(logits, ilens.cpu().to(torch.int64), batch_first=True, enforce_sorted=False)
outputs, (_, _) = self.postnet(logits)
outputs = nn.utils.rnn.pad_packed_sequence(outputs, batch_first=True, padding_value=-1, total_length=maxlen)[0]
outputs = [output[:ilens[i].to(torch.int).item()] for i, output in enumerate(outputs)]
@@ -91,7 +89,6 @@
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, )
@@ -231,7 +228,7 @@
pred[i] = pred[i - 1]
else:
pred[i] = 0
- pred = [self.reporter.inv_mapping_func(i, self.mapping_dict) for i in pred]
+ pred = [self.inv_mapping_func(i) for i in pred]
decisions = [bin(num)[2:].zfill(self.max_n_speaker)[::-1] for num in pred]
decisions = torch.from_numpy(
np.stack([np.array([int(i) for i in dec]) for dec in decisions], axis=0)).to(logit.device).to(
@@ -239,5 +236,15 @@
decisions = decisions[:, :n_speaker]
return decisions
+ def inv_mapping_func(self, label):
+
+ if not isinstance(label, int):
+ label = int(label)
+ if label in self.mapping_dict['label2dec'].keys():
+ num = self.mapping_dict['label2dec'][label]
+ else:
+ num = -1
+ return num
+
def collect_feats(self, **batch: torch.Tensor) -> Dict[str, torch.Tensor]:
pass
\ No newline at end of file
--
Gitblit v1.9.1