返回 F5-TTS
config.pbtxt
1 # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 name: "f5_tts"
16 backend: "python"
17 max_batch_size: 4
18 dynamic_batching {
19 max_queue_delay_microseconds: 1000
20 }
21 parameters [
22 {
23 key: "vocab_file"
24 value: { string_value: "${vocab}"}
25 },
26 {
27 key: "model_path",
28 value: {string_value:"${model}"}
29 },
30 {
31 key: "tllm_model_dir",
32 value: {string_value:"${trtllm}"}
33 },
34 {
35 key: "reference_audio_sample_rate",
36 value: {string_value:"24000"}
37 },
38 {
39 key: "vocoder",
40 value: {string_value:"${vocoder}"}
41 }
42 ]
43
44 input [
45 {
46 name: "reference_wav"
47 data_type: TYPE_FP32
48 dims: [-1]
49 optional: True
50 },
51 {
52 name: "reference_wav_len"
53 data_type: TYPE_INT32
54 dims: [1]
55 optional: True
56 },
57 {
58 name: "reference_text"
59 data_type: TYPE_STRING
60 dims: [1]
61 },
62 {
63 name: "target_text"
64 data_type: TYPE_STRING
65 dims: [1]
66 }
67 ]
68 output [
69 {
70 name: "waveform"
71 data_type: TYPE_FP32
72 dims: [ -1 ]
73 }
74 ]
75
76 instance_group [
77 {
78 count: 1
79 kind: KIND_GPU
80 }
81 ]
81 lines Plain Text