From ecead60d25954e092ee46f79f17d7ee79da642ff Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期六, 05 八月 2023 17:55:06 +0800
Subject: [PATCH] update repo
---
funasr/models/e2e_diar_eend_ola.py | 17 +++++------------
1 files changed, 5 insertions(+), 12 deletions(-)
diff --git a/funasr/models/e2e_diar_eend_ola.py b/funasr/models/e2e_diar_eend_ola.py
index af0fd62..0225a7a 100644
--- a/funasr/models/e2e_diar_eend_ola.py
+++ b/funasr/models/e2e_diar_eend_ola.py
@@ -12,7 +12,7 @@
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.losses import fast_batch_pit_n_speaker_loss, standard_loss, cal_power_loss
+from funasr.modules.eend_ola.utils.losses import standard_loss, cal_power_loss, fast_batch_pit_n_speaker_loss
from funasr.modules.eend_ola.utils.power import create_powerlabel
from funasr.modules.eend_ola.utils.power import generate_mapping_dict
from funasr.torch_utils.device_funcs import force_gatherable
@@ -109,23 +109,17 @@
def forward(
self,
speech: List[torch.Tensor],
- speech_lengths: torch.Tensor, # num_frames of each sample
speaker_labels: List[torch.Tensor],
- speaker_labels_lengths: torch.Tensor, # num_speakers of each sample
orders: torch.Tensor,
) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
# Check that batch_size is unified
- assert (
- len(speech)
- == len(speech_lengths)
- == len(speaker_labels)
- == len(speaker_labels_lengths)
- ), (len(speech), len(speech_lengths), len(speaker_labels), len(speaker_labels_lengths))
+ assert (len(speech) == len(speaker_labels)), (len(speech), len(speaker_labels))
+ speech_lengths = torch.tensor([len(sph) for sph in speech]).to(torch.int64)
+ speaker_labels_lengths = torch.tensor([spk.shape[-1] for spk in speaker_labels]).to(torch.int64)
batch_size = len(speech)
# Encoder
- speech = [s[:s_len] for s, s_len in zip(speech, speech_lengths)]
encoder_out = self.forward_encoder(speech, speech_lengths)
# Encoder-decoder attractor
@@ -163,12 +157,11 @@
def estimate_sequential(self,
speech: torch.Tensor,
- speech_lengths: torch.Tensor,
n_speakers: int = None,
shuffle: bool = True,
threshold: float = 0.5,
**kwargs):
- speech = [s[:s_len] for s, s_len in zip(speech, speech_lengths)]
+ speech_lengths = torch.tensor([len(sph) for sph in speech]).to(torch.int64)
emb = self.forward_encoder(speech, speech_lengths)
if shuffle:
orders = [np.arange(e.shape[0]) for e in emb]
--
Gitblit v1.9.1