Yiwei Ding
Yiwei Ding
The base conda env is: `conda create -n unispeech python=3.8` when I run `pip install --require-hashes -r requirements.txt` under [speaker_verification](https://github.com/microsoft/UniSpeech/tree/main/downstreams/speaker_verification). The error will appear: ``` Collecting numpy=1.16.5 ERROR: In --require-hashes...
Two question: 1. Where does the [self.best_score](https://github.com/s3prl/s3prl/blob/26113e9febbaaee6311f8c2cdd9475dc495acce9/s3prl/downstream/sv_voxceleb1/expert.py#L268) do the initialization? I can't find where it is initialized by global search. If I initialize it at init, it will report an...
I refer to the README for SV task training using Wavlm as the upstream. The usage of this [Demo](https://github.com/s3prl/s3prl/blob/master/s3prl/downstream/docs/superb.md#asv-automatic-speaker-verification) is to train on vox1's Dev and test it on vox1's...
I refer to the documentation [here](https://github.com/s3prl/s3prl/blob/master/s3prl/downstream/docs/superb.md#asv-automatic-speaker-verification). I can successfully run the training of wavlm_large by: `python3 run_downstream.py -m train -u wavlm_large -d sv_voxceleb1 -n wavlm_large ` Then I from [here](https://github.com/microsoft/UniSpeech/tree/main/downstreams/speaker_verification)...
`Traceback (most recent call last): File "scripts/train.py", line 270, in main(sys.argv[1:]) File "scripts/train.py", line 237, in main config.img_alpha_weight_dir) File "scripts/train.py", line 74, in setup_dataset train_raw, test_raw = datasets.split_dataset(dataset) File "G:\github\portrait_matting\scripts\datasets\common.py",...
Generally speaking, the backbone will fix its parameters when extracting features. But I don't seem to see fixed-parameter operations when [loading the backbone](https://github.com/yangsenius/TransPose/blob/dab9007b6f61c9c8dce04d61669a04922bbcd148/lib/models/transpose_h.py#L690).
想到一个加一个吧。 - [ ] 1. rasa run和rasa run actions的区别？ - [ ] 2. Rasa和RasaX的区别？ - [ ] 3. Rasa在何处调用Bert? - [ ] 4. 回译文本工具的作用是什么？ - [x] 5. API的形式调用Rasa的地址是多少以及需要传递什么参数？([答案](https://github.com/Dustyposa/rasa_ch_faq/issues/2#issuecomment-804022047))
Thank you for sharing your work. I have some problem running it, and I suspect it may be a version inconsistency problem. So what are the **specific version** numbers of...
> /path/to/data/folder: |-rgb |-XXXXX.png |-YYYYY.png |-ZZZZZ.png |-... |-trimap |-XXXXX.png |-YYYYY.png |-ZZZZZ.png |-... |-val_set.txt
Hi! How to test the pre-trained model? I don't see `test.py` or `inference.py` And if there are any image or video to show EmotionNet visualized results