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
| # Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
| #
| # 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.
|
| name: "sensevoice"
| platform: "ensemble"
| max_batch_size: 16
|
| input [
| {
| name: "WAV"
| data_type: TYPE_FP32
| dims: [-1]
| },
| {
| name: "WAV_LENS"
| data_type: TYPE_INT32
| dims: [1]
| },
| {
| name: "LANGUAGE"
| data_type: TYPE_INT32
| dims: [1]
| },
| {
| name: "TEXT_NORM"
| data_type: TYPE_INT32
| dims: [1]
| }
| ]
|
| output [
| {
| name: "TRANSCRIPTS"
| data_type: TYPE_STRING
| dims: [1]
| }
| ]
|
| ensemble_scheduling {
| step [
| {
| model_name: "feature_extractor"
| model_version: -1
| input_map {
| key: "wav"
| value: "WAV"
| }
| input_map {
| key: "wav_lens"
| value: "WAV_LENS"
| }
| output_map {
| key: "speech"
| value: "SPEECH"
| }
| output_map {
| key: "speech_lengths"
| value: "SPEECH_LENGTHS"
| }
| },
| {
| model_name: "encoder"
| model_version: -1
| input_map {
| key: "speech"
| value: "SPEECH"
| }
| input_map {
| key: "speech_lengths"
| value: "SPEECH_LENGTHS"
| }
| input_map {
| key: "language"
| value: "LANGUAGE"
| }
| input_map {
| key: "textnorm"
| value: "TEXT_NORM"
| }
| output_map {
| key: "ctc_logits"
| value: "ctc_logits"
| }
| output_map {
| key: "encoder_out_lens"
| value: "encoder_out_lens"
| }
| },
| {
| model_name: "scoring"
| model_version: -1
| input_map {
| key: "ctc_logits"
| value: "ctc_logits"
| }
| input_map {
| key: "encoder_out_lens"
| value: "encoder_out_lens"
| }
| output_map {
| key: "OUTPUT0"
| value: "TRANSCRIPTS"
| }
| }
| ]
| }
|
|
