Upload 4 files
Browse files- README.md +25 -3
- campplus_cn_common.pt +3 -0
- config.yaml +23 -0
- configuration.json +23 -0
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- zh
|
| 5 |
+
tags:
|
| 6 |
+
- speaker-verification
|
| 7 |
+
- speaker-recognition
|
| 8 |
+
- speaker-embedding
|
| 9 |
+
- speech
|
| 10 |
+
- audio
|
| 11 |
+
- campplus
|
| 12 |
+
pipeline_tag: audio-classification
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# CAMPPlus Speaker Encoder
|
| 16 |
+
|
| 17 |
+
This directory contains a local copy of the CAMPPlus speaker verification model, originally released through ModelScope / 3D-Speaker. The model is used to extract speaker embeddings from speech, while the original model architecture, weights, authorship, and license remain attributed to the original authors.
|
| 18 |
+
|
| 19 |
+
The upstream 3D-Speaker project is released under the `Apache-2.0` license. When using, redistributing, or citing these files, please keep the original author information, model link, and license notice.
|
| 20 |
+
|
| 21 |
+
Original links:
|
| 22 |
+
|
| 23 |
+
- ModelScope: https://www.modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common
|
| 24 |
+
- 3D-Speaker: https://github.com/modelscope/3D-Speaker
|
| 25 |
+
- License: https://www.apache.org/licenses/LICENSE-2.0
|
campplus_cn_common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ffb1a55d04bac4a9b7ed80497cb731909985c9b55d120fce04b851a697886c
|
| 3 |
+
size 14173135
|
config.yaml
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# This is an example that demonstrates how to configure a model file.
|
| 2 |
+
# You can modify the configuration according to your own requirements.
|
| 3 |
+
|
| 4 |
+
# to print the register_table:
|
| 5 |
+
# from funasr.register import tables
|
| 6 |
+
# tables.print()
|
| 7 |
+
|
| 8 |
+
# network architecture
|
| 9 |
+
model: CAMPPlus
|
| 10 |
+
model_conf:
|
| 11 |
+
feat_dim: 80
|
| 12 |
+
embedding_size: 192
|
| 13 |
+
growth_rate: 32
|
| 14 |
+
bn_size: 4
|
| 15 |
+
init_channels: 128
|
| 16 |
+
config_str: 'batchnorm-relu'
|
| 17 |
+
memory_efficient: True
|
| 18 |
+
output_level: 'segment'
|
| 19 |
+
|
| 20 |
+
# frontend related
|
| 21 |
+
frontend: WavFrontend
|
| 22 |
+
frontend_conf:
|
| 23 |
+
fs: 16000
|
configuration.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"framework": "pytorch",
|
| 3 |
+
"task": "speaker-verification",
|
| 4 |
+
"model_config": "config.yaml",
|
| 5 |
+
"model_file": "campplus_cn_common.bin",
|
| 6 |
+
"model": {
|
| 7 |
+
"type": "cam++-sv",
|
| 8 |
+
"model_config": {
|
| 9 |
+
"sample_rate": 16000,
|
| 10 |
+
"fbank_dim": 80,
|
| 11 |
+
"emb_size": 192
|
| 12 |
+
},
|
| 13 |
+
"pretrained_model": "campplus_cn_common.bin",
|
| 14 |
+
"yesOrno_thr": 0.31
|
| 15 |
+
},
|
| 16 |
+
"pipeline": {
|
| 17 |
+
"type": "speaker-verification"
|
| 18 |
+
},
|
| 19 |
+
"file_path_metas": {
|
| 20 |
+
"init_param":"campplus_cn_common.bin",
|
| 21 |
+
"config":"config.yaml"
|
| 22 |
+
}
|
| 23 |
+
}
|