offline_recognizer.py
5.0 KB
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
154
155
156
157
158
159
160
161
162
163
164
165
# Copyright (c) 2023 by manyeyes
from pathlib import Path
from typing import List
from _sherpa_onnx import (
OfflineFeatureExtractorConfig,
OfflineRecognizer as _Recognizer,
OfflineRecognizerConfig,
OfflineStream,
OfflineModelConfig,
OfflineTransducerModelConfig,
OfflineParaformerModelConfig,
)
def _assert_file_exists(f: str):
assert Path(f).is_file(), f"{f} does not exist"
class OfflineRecognizer(object):
"""A class for offline speech recognition.
Please refer to the following files for usages
- https://github.com/k2-fsa/sherpa-onnx/blob/master/sherpa-onnx/python/tests/test_offline_recognizer.py
- https://github.com/k2-fsa/sherpa-onnx/blob/master/python-api-examples/offline-decode-files.py
"""
@classmethod
def from_transducer(
cls,
encoder: str,
decoder: str,
joiner: str,
tokens: str,
num_threads: int,
sample_rate: int = 16000,
feature_dim: int = 80,
decoding_method: str = "greedy_search",
debug: bool = False,
):
"""
Please refer to
`<https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html>`_
to download pre-trained models for different languages, e.g., Chinese,
English, etc.
Args:
tokens:
Path to ``tokens.txt``. Each line in ``tokens.txt`` contains two
columns::
symbol integer_id
encoder:
Path to ``encoder.onnx``.
decoder:
Path to ``decoder.onnx``.
joiner:
Path to ``joiner.onnx``.
num_threads:
Number of threads for neural network computation.
sample_rate:
Sample rate of the training data used to train the model.
feature_dim:
Dimension of the feature used to train the model.
decoding_method:
Support only greedy_search for now.
debug:
True to show debug messages.
"""
self = cls.__new__(cls)
model_config = OfflineModelConfig(
transducer=OfflineTransducerModelConfig(
encoder_filename=encoder,
decoder_filename=decoder,
joiner_filename=joiner,
),
paraformer=OfflineParaformerModelConfig(model=""),
tokens=tokens,
num_threads=num_threads,
debug=debug,
)
feat_config = OfflineFeatureExtractorConfig(
sampling_rate=sample_rate,
feature_dim=feature_dim,
)
recognizer_config = OfflineRecognizerConfig(
feat_config=feat_config,
model_config=model_config,
decoding_method=decoding_method,
)
self.recognizer = _Recognizer(recognizer_config)
return self
@classmethod
def from_paraformer(
cls,
paraformer: str,
tokens: str,
num_threads: int,
sample_rate: int = 16000,
feature_dim: int = 80,
decoding_method: str = "greedy_search",
debug: bool = False,
):
"""
Please refer to
`<https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html>`_
to download pre-trained models for different languages, e.g., Chinese,
English, etc.
Args:
tokens:
Path to ``tokens.txt``. Each line in ``tokens.txt`` contains two
columns::
symbol integer_id
paraformer:
Path to ``paraformer.onnx``.
num_threads:
Number of threads for neural network computation.
sample_rate:
Sample rate of the training data used to train the model.
feature_dim:
Dimension of the feature used to train the model.
decoding_method:
Valid values are greedy_search, modified_beam_search.
debug:
True to show debug messages.
"""
self = cls.__new__(cls)
model_config = OfflineModelConfig(
transducer=OfflineTransducerModelConfig(
encoder_filename="", decoder_filename="", joiner_filename=""
),
paraformer=OfflineParaformerModelConfig(model=paraformer),
tokens=tokens,
num_threads=num_threads,
debug=debug,
)
feat_config = OfflineFeatureExtractorConfig(
sampling_rate=sample_rate,
feature_dim=feature_dim,
)
recognizer_config = OfflineRecognizerConfig(
feat_config=feat_config,
model_config=model_config,
decoding_method=decoding_method,
)
self.recognizer = _Recognizer(recognizer_config)
return self
def create_stream(self):
return self.recognizer.create_stream()
def decode_stream(self, s: OfflineStream):
self.recognizer.decode_stream(s)
def decode_streams(self, ss: List[OfflineStream]):
self.recognizer.decode_streams(ss)