-
Hi @echarlaix @IlyasMoutawwakil
The bug comes from SentenceTransformer, when I loading a sentence transformer model like `IPEXModel.from_pretrained("intfloat/e5-mistral-7b-instruct", export=True)`…
-
First of all, thank you very much for making our lives easier with the work you do at huggingface, congratulations!
We have a model based on the encoder-decoder architecture, made up of 2 RoBERTa. Th…
-
I tried to reproduce your work on vox1-o, but cannot reach the performance described in the paper, here is my implementation
wavlm-large from huggingface/microsoft/wavlm-large
ecapa-tdnn-base from …
-
### Context
Worked in phi-3, model id from hugging face: **microsoft/Phi-3-mini-128k-instruct**.
opevino-version: 2024.3.0-15583-df6a25800d3
i'm using transformers: **transformers 4.39.3**
bel…
-
I would like to ask you about how much information you can use to achieve such good results, and how long the training lasts.
-
This work is highly significant!
But I had some problems with the implementation of the dataset, which is stored in the following format
datasets
|-EmoV-DB
|--bea_Amused ....
|----***.wav.....
…
-
Have you tried using Wavlm, which has been fine-tuned on an ASR dataset, to extract semantic features for querying KNN instead of directly using SSL features? Using KNN to obtain timestamps only, then…
-
Hey! I know you wrote about this here: https://github.com/bshall/knn-vc/issues/23
I think I'm going to go ahead and try those steps now
However, I did find this 48K HiFiGAN model someone trained…
-
Thanks for your sharing. Could you provide the missing file "datasets.py" that is used in data preparation?
![Screenshot 2024-03-12 at 4 45 47 PM](https://github.com/ETZET/SpeechEmotionAVLearning/ass…
-
Hi, did you try train a different language for voice conversion from pretrained models ? Can you give some hints for this issue, which modules should be re-trained ?