Merge pull request #355 from alibaba-damo-academy/dev_dzh

zhifu gao

2023-04-14 511caf64ff2cd61fd45a9a29901336055336a994

Merge pull request #355 from alibaba-damo-academy/dev_dzh

add authority

 egs_modelscope/speaker_diarization/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/infer.py

@@ -1,3 +1,9 @@
"""
Author: Speech Lab, Alibaba Group, China
TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
https://arxiv.org/abs/2303.05397
"""

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks


 egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py

@@ -1,3 +1,9 @@
"""
Author: Speech Lab, Alibaba Group, China
SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
https://arxiv.org/abs/2211.10243
"""

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks


 funasr/models/e2e_diar_sond.py

@@ -36,8 +36,12 @@


class DiarSondModel(AbsESPnetModel):
    """Speaker overlap-aware neural diarization model
    reference: https://arxiv.org/abs/2211.10243
    """
    Author: Speech Lab, Alibaba Group, China
    SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
    https://arxiv.org/abs/2211.10243
    TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
    https://arxiv.org/abs/2303.05397
    """

    def __init__(

 funasr/models/e2e_sv.py

@@ -1,3 +1,7 @@
"""
Author: Speech Lab, Alibaba Group, China
"""

import logging
from contextlib import contextmanager
from distutils.version import LooseVersion

 funasr/models/encoder/resnet34_encoder.py

@@ -406,6 +406,12 @@
            tf2torch_tensor_name_prefix_torch="encoder",
            tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
    ):
        """
        Author: Speech Lab, Alibaba Group, China
        SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
        https://arxiv.org/abs/2211.10243
        """

        super(ResNet34Diar, self).__init__(
            input_size,
            use_head_conv=use_head_conv,
@@ -633,6 +639,12 @@
            tf2torch_tensor_name_prefix_torch="encoder",
            tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
    ):
        """
        Author: Speech Lab, Alibaba Group, China
        TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
        https://arxiv.org/abs/2303.05397
        """

        super(ResNet34SpL2RegDiar, self).__init__(
            input_size,
            use_head_conv=use_head_conv,

 funasr/tasks/diar.py

@@ -1,3 +1,11 @@
"""
Author: Speech Lab, Alibaba Group, China
SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
https://arxiv.org/abs/2211.10243
TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
https://arxiv.org/abs/2303.05397
"""

import argparse
import logging
import os

 funasr/tasks/sv.py

@@ -1,3 +1,7 @@
"""
Author: Speech Lab, Alibaba Group, China
"""

import argparse
import logging
import os