nywhere

Results 8 comments of nywhere

TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.

+1

Request for AutoShot Model Weights via an Alternative Method

+1 I have the same issue

failed to get cpuinfo on aws lambda arm64

Any update?

[Feature request] ONNX need support opset MatMulInteger input 4bit

I just went into the same issue.

STL reader can generate 4 digits milliseconds time

It actually comes from ClockTime: ``` >>> from ttconv.time_code import ClockTime >>> from fractions import Fraction >>> f = Fraction(41039999,7500) >>> c = ClockTime.from_seconds(f) >>> c.get_milliseconds() 1000 ```

STL reader can generate 4 digits milliseconds time

@palemieux Yes, that fixes the issue. Thanks!

Option to not deregister prior AWS Batch Job Definition revisions

Very surprising this issue hasn’t been addressed by AWS. What is the purpose of revisions if only the last one is usable?

VTT Writer performances

The first option definitely makes sense. Option 2 would be nice too. Maybe some caching on computed style could help too, if applicable of course.