saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-27 20:02:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update wheel path to Whisper custom export script (#15739)

Browse source 
### Description
This PR updates the documentation for using the Whisper custom export
scripts via the wheel.



### Motivation and Context
The path should say
`onnxruntime.transformers.models.whisper.convert_to_onnx` instead of
`onnxruntime.transformers.models.convert_to_onnx`.
This commit is contained in:
kunal-vaishnavi 2023-04-29 17:32:34 -07:00 committed by GitHub
parent 4fbc08e3c2
commit 7ae01cec15
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
onnxruntime/python/tools/transformers/models/whisper/README.md
View file

@ -26,7 +26,7 @@ Export + Optimize for FP32
$ python3 convert_to_onnx.py -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp32
# From wheel:
$ python3 -m onnxruntime.transformers.models.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp32
$ python3 -m onnxruntime.transformers.models.whisper.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp32
```
Export + Optimize for FP16 and GPU
@ -35,7 +35,7 @@ Export + Optimize for FP16 and GPU
$ python3 convert_to_onnx.py -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp16 --use_gpu
# From wheel:
$ python3 -m onnxruntime.transformers.models.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp16 --use_gpu
$ python3 -m onnxruntime.transformers.models.whisper.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --optimize_onnx --precision fp16 --use_gpu
```
Export + Quantize for INT8
@ -44,5 +44,5 @@ Export + Quantize for INT8
$ python3 convert_to_onnx.py -m openai/whisper-tiny --output whispertiny --use_external_data_format --precision int8 --quantize_embedding_layer
# From wheel:
$ python3 -m onnxruntime.transformers.models.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --precision int8 --quantize_embedding_layer
$ python3 -m onnxruntime.transformers.models.whisper.convert_to_onnx -m openai/whisper-tiny --output whispertiny --use_external_data_format --precision int8 --quantize_embedding_layer
```