EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
15
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Export speaker verification models from NeMo to ONNX (#526)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-01-13 19:49:45 +08:00
committed by GitHub
parent afc81ec122
commit 68a525a024
10 changed files with 448 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python-api-examples/speaker-identification.py
View File

@@ -29,7 +29,7 @@ Please visit
https://github.com/k2-fsa/sherpa-onnx/releases/tag/speaker-recongition-models
to download a model. An example is given below:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-recongition-models/zh_cnceleb_resnet34.onnx
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-recongition-models/wespeaker_zh_cnceleb_resnet34.onnx
Note that `zh` means Chinese, while `en` means English.
@@ -39,7 +39,7 @@ Assume the filename of the text file is speaker.txt.
python3 ./python-api-examples/speaker-identification.py \
--speaker-file ./speaker.txt \
--model ./zh_cnceleb_resnet34.onnx
--model ./wespeaker_zh_cnceleb_resnet34.onnx
"""
import argparse
import queue