-
### 🐛 Describe the bug
I noticed a qualitative regression in the inference quality when compiling a segformer-b0 model from the `transformers` library. This regression was introduced in the 2.5.0 rel…
-
-
## TODOs
- [ ] Fix the speaker embedding finetuning code https://github.com/lenML/ChatTTS-Forge/blob/318d33f8d0b1451a39b3cbc94debca7f4f21dfca/modules/finetune/train_speaker.py#L15-L26
- [ ] Use the …
-
We have successfully run the docker containers but we don't know how to load pre-trained weights
encoder = torch.load('model_weights/encoder_resnet34_0.061650436371564865.pt')
decoder = torch.load('…
-
Thanks for your work.
You'v mentioned that the `video_latent.pt` is the video latent encoded by SV3D encoder. So where could I find the weight of this encoder? It seems that the weight in `sv3d_p.sa…
-
Hi there! I have tried the weight of decoder you provided here:
[WM weights of latent decoder](https://dl.fbaipublicfiles.com/ssl_watermarking/sd2_decoder.pth)
and I generate an image using code pro…
-
**Describe the bug**
Model I am using (trocr-base-stage1.pt, trocr-base-printed.pt etc. TrOCR pretained models):
The problem arises when using:
pic_inference.py
A clear and concise descriptio…
-
### 操作是从启动app.exe到执行第一次声音合成
Starting...
2024-08-08 23:20:32,817 - modelscope - INFO - PyTorch version 2.1.2+cu118 Found.
2024-08-08 23:20:32,818 - modelscope - INFO - Loading ast index from C:\User…
-
## Is your feature request related to a problem? Please describe.
Adding bootstrap functionality that can take `base_model` and pretrained prompt models, i.e `encoder.pt` or `decoder.pt` (or both) …
-
I followed your instructions for the SFT training and I got the .pt trained weights,
then I run:
python train_rm.py -b 2 -n experiment_name -p "./runs/sft_javSFT2_202405021344/sft_javSFT2_20240502…