-
Notifications
You must be signed in to change notification settings - Fork 56
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Ygr avsr #25
Conversation
"visual": inputBatch[2], #torch.Size([4, 146, 1, 112, 112]) | ||
"vis_len": inputBatch[3], #torch.Size([4]) | ||
|
||
"targetoutBatch": targetoutBatch, #torch.Size([4, 50]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To delete
visual = kwargs.get("visual", None) #torch.Size([2, 151, 1, 112, 112]) | ||
vis_len = kwargs.get("vis_len", None) #tensor([ 77, 151], device='cuda:0', dtype=torch.int32) | ||
maskw2v = kwargs.get("maskw2v", None) #True | ||
targetoutBatch = kwargs.get("targetoutBatch", None) #torch.Size([2, 29]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To delete
@@ -184,13 +187,25 @@ def forward(self, | |||
audio_mel_post_mask = kwargs.get("audio_mel_post_mask", None) # 2x downsample for whisper | |||
audio_mask = kwargs.get("audio_mask", None) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
name should change to audio_mel_mask
@@ -184,13 +187,25 @@ def forward(self, | |||
audio_mel_post_mask = kwargs.get("audio_mel_post_mask", None) # 2x downsample for whisper | |||
audio_mask = kwargs.get("audio_mask", None) | |||
|
|||
audio = kwargs.get("audio", None) #torch.Size([2, 96480]) | |||
audiomask = kwargs.get("audiomask", None) #删 #torch.Size([2, 96480]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
name should change to audio_mask
"vis_len": inputBatch[3], #torch.Size([4]) | ||
|
||
"targetoutBatch": targetoutBatch, #torch.Size([4, 50]) | ||
"targetLenBatch": targetLenBatch.long(), #torch.Size([4]) | ||
'maskw2v': True, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should always be false
merge AVSR