mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-19 05:54:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support int8 quantization in decoder

Browse Source
This commit is contained in:
pkufool 2023-06-29 12:15:06 +08:00
parent 9c2172c1c4
commit 3544665ace
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs/librispeech/ASR/zipformer/export-onnx-streaming.py
View File

@ -757,7 +757,7 @@ def main():
quantize_dynamic(
model_input=decoder_filename,
model_output=decoder_filename_int8,
op_types_to_quantize=["MatMul"],
op_types_to_quantize=["MatMul", "Gather"],
weight_type=QuantType.QInt8,
)

2
egs/librispeech/ASR/zipformer/export-onnx.py
View File

@ -602,7 +602,7 @@ def main():
quantize_dynamic(
model_input=decoder_filename,
model_output=decoder_filename_int8,
op_types_to_quantize=["MatMul"],
op_types_to_quantize=["MatMul", "Gather"],
weight_type=QuantType.QInt8,
)