Rasmus Toivanen

Results 10 issues of Rasmus Toivanen

Will you release pretrained models?

Has anyone tried running the pipeline with TPUs? Any success? Any examples?

Please add dependencyfile or instructions on environment setup

Hi, Is it possible to run this with WSL2? The ONNX Resnet example breaks with Windows11 WSL2 ![image](https://user-images.githubusercontent.com/25264037/198390108-73e881f5-a018-454f-b2b7-e9699165b593.png)

Hi, I made a small demo here https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles which uses these models. Now I am trying to convert models created during Huggingface Whisper finetuning event to be used with this...

question

I try to finetune model for TTS. I have myself prepared train_manifest.json and eval_manifest.json files with coding instead of using the datasets scripts. My train_manifest.json should look like the same...

![image](https://user-images.githubusercontent.com/25264037/164318827-c1ef17e0-0cac-49be-a6d2-983d1c6d8100.png) I have successfully tested this with regular model 300m parameter model and it runs great. 5 sec of audio in around 0.8 seconds However when I convert to onnx/quant.onnx...

Hi, Could you please include some examples how to load these files as a language_model_learner. I am having issues with loading the finnish_enc.pth and finnish_icos.pkl to fastai language_model_learner. I am...

### Describe the problem If chromadb would support images as argument as in: https://docs.cohere.com/reference/embed it would be nice ### Describe the proposed solution ``` import chromadb.utils.embedding_functions as embedding_functions cohere_ef =...

enhancement

Downloading models from Kaggle and converting manually is cumbersome. Please provide direct conversion from models hosted in Huggingface.