File size: 5,079 Bytes
c58376d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright      2024  Xiaomi Corp.        (authors: Fangjun Kuang)
#
# See LICENSE for clarification regarding multiple authors
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import wave
from typing import List, Tuple

import numpy as np
import sherpa_onnx
from huggingface_hub import hf_hub_download


def read_wave(wave_filename: str) -> Tuple[np.ndarray, int]:
    """
    Args:
      wave_filename:
        Path to a wave file. It should be single channel and each sample should
        be 16-bit. Its sample rate does not need to be 16kHz.
    Returns:
      Return a tuple containing:
       - A 1-D array of dtype np.float32 containing the samples, which are
       normalized to the range [-1, 1].
       - sample rate of the wave file
    """

    with wave.open(wave_filename) as f:
        assert f.getnchannels() == 1, f.getnchannels()
        assert f.getsampwidth() == 2, f.getsampwidth()  # it is in bytes
        num_samples = f.getnframes()
        samples = f.readframes(num_samples)
        samples_int16 = np.frombuffer(samples, dtype=np.int16)
        samples_float32 = samples_int16.astype(np.float32)

        samples_float32 = samples_float32 / 32768
        return samples_float32, f.getframerate()


def _get_nn_model_filename(
    repo_id: str,
    filename: str,
    subfolder: str = ".",
) -> str:
    nn_model_filename = hf_hub_download(
        repo_id=repo_id,
        filename=filename,
        subfolder=subfolder,
    )
    return nn_model_filename


def get_speaker_segmentation_model(repo_id) -> List[str]:
    assert repo_id in ("pyannote/segmentation-3.0",)

    if repo_id == "pyannote/segmentation-3.0":
        return _get_nn_model_filename(
            repo_id="csukuangfj/sherpa-onnx-pyannote-segmentation-3-0",
            filename="model.onnx",
        )


def get_speaker_embedding_model(model_name) -> List[str]:
    assert (
        model_name
        in three_d_speaker_embedding_models
        + nemo_speaker_embedding_models
        + wespeaker_embedding_models
    )

    return _get_nn_model_filename(
        repo_id="csukuangfj/speaker-embedding-models",
        filename=model_name,
    )


def get_speaker_diarization(
    segmentation_model: str, embedding_model: str, num_clusters: int, threshold: float
):
    segmentation = get_speaker_segmentation_model(segmentation_model)
    embedding = get_speaker_embedding_model(embedding_model)

    config = sherpa_onnx.OfflineSpeakerDiarizationConfig(
        segmentation=sherpa_onnx.OfflineSpeakerSegmentationModelConfig(
            pyannote=sherpa_onnx.OfflineSpeakerSegmentationPyannoteModelConfig(
                model=segmentation
            ),
        ),
        embedding=sherpa_onnx.SpeakerEmbeddingExtractorConfig(model=embedding),
        clustering=sherpa_onnx.FastClusteringConfig(
            num_clusters=num_clusters,
            threshold=threshold,
        ),
        min_duration_on=0.3,
        min_duration_off=0.5,
    )
    if not config.validate():
        raise RuntimeError(
            "Please check your config and make sure all required files exist"
        )

    return sherpa_onnx.OfflineSpeakerDiarization(config)
    pass


speaker_segmentation_models = ["pyannote/segmentation-3.0"]


nemo_speaker_embedding_models = [
    "nemo_en_speakerverification_speakernet.onnx",
    "nemo_en_titanet_large.onnx",
    "nemo_en_titanet_small.onnx",
]

three_d_speaker_embedding_models = [
    "3dspeaker_speech_campplus_sv_en_voxceleb_16k.onnx",
    "3dspeaker_speech_campplus_sv_zh-cn_16k-common.onnx",
    "3dspeaker_speech_campplus_sv_zh_en_16k-common_advanced.onnx",
    "3dspeaker_speech_eres2net_base_200k_sv_zh-cn_16k-common.onnx",
    "3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx",
    "3dspeaker_speech_eres2net_large_sv_zh-cn_3dspeaker_16k.onnx",
    "3dspeaker_speech_eres2net_sv_en_voxceleb_16k.onnx",
    "3dspeaker_speech_eres2net_sv_zh-cn_16k-common.onnx",
    "3dspeaker_speech_eres2netv2_sv_zh-cn_16k-common.onnx",
]
wespeaker_embedding_models = [
    "wespeaker_en_voxceleb_CAM++.onnx",
    "wespeaker_en_voxceleb_CAM++_LM.onnx",
    "wespeaker_en_voxceleb_resnet152_LM.onnx",
    "wespeaker_en_voxceleb_resnet221_LM.onnx",
    "wespeaker_en_voxceleb_resnet293_LM.onnx",
    "wespeaker_en_voxceleb_resnet34.onnx",
    "wespeaker_en_voxceleb_resnet34_LM.onnx",
    "wespeaker_zh_cnceleb_resnet34.onnx",
    "wespeaker_zh_cnceleb_resnet34_LM.onnx",
]

embedding2models = {
    "3D-Speaker": three_d_speaker_embedding_models,
    "NeMo": nemo_speaker_embedding_models,
    "WeSpeaker": wespeaker_embedding_models,
}