jpohhhh commited on
Commit
4dfa6d4
1 Parent(s): f9fb13c

Update Whisper models

Browse files

Whisper on Web: required significant refactor

TL;DR:
ONNX Web doesn't support ORT extensions.

So, arbitrary audio bytes can no longer be passed as input to Whisper.

This is for the best: there's a complex web of constraints for streaming audio
that limited things to signed PCM-16 little endian anyway.

This also required new models that don't attempt to decode audio.

This also means ORTExtensions can be removed, as it was only included to
get support for audio decoding.

That should be left to a later commit, that also checks on what exactly
ORTExtensions does (ex. IIRC I saw LLM work for it, it may be best to remove
the assets from the build to save about 10 MB, but leave the code in case
its useful again)

Files changed (3) hide show
  1. whisper_base.onnx +2 -2
  2. whisper_small.onnx +2 -2
  3. whisper_tiny.onnx +2 -2
whisper_base.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ce7ec0fe2cc74242c4e0b33c5c42cb1eef456142506649fdbe0818f24d2092d
3
- size 139097531
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b266a859997eda7e59d07798770c7f63313fe96b8e3f2f358d847d55f6f5eeb
3
+ size 139097248
whisper_small.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0db75903517cfd9c4cca706b86d970dd2a6f1e36b208fc450a529097a756ac27
3
- size 442795612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98cb88932b0ab7f3415242b43fffe5a5a92afc8baceeac3567455240fe6ff048
3
+ size 442795329
whisper_tiny.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bee79c83c3c6ca1694deb9c585cacaf02410ce3f8093be1b6e3933ea1732869
3
- size 74823735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b7c806032cf080f185330ad4c593e8d1ed97f61ce354f844453c7173933d14
3
+ size 74823452