Fill-Mask
Transformers
Safetensors
PyTorch
English
saute
feature-extraction
masked-language-modeling
dialogue
speaker-aware
transformer
custom_code
Instructions to use JustinDuc/saute with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JustinDuc/saute with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="JustinDuc/saute", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JustinDuc/saute", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -72,7 +72,7 @@ It avoids the quadratic cost of full self-attention by summarizing per-speaker m
|
|
| 72 |
|
| 73 |
## 📚 Citation / Paper
|
| 74 |
|
| 75 |
-
📄 [SAUTE: Speaker-Aware Utterance Embedding Unit (PDF)](https://github.com/user-attachments/files/
|
| 76 |
|
| 77 |
---
|
| 78 |
|
|
|
|
| 72 |
|
| 73 |
## 📚 Citation / Paper
|
| 74 |
|
| 75 |
+
📄 [SAUTE: Speaker-Aware Utterance Embedding Unit (PDF)](https://github.com/user-attachments/files/20689695/SAUTE_Speaker_Aware_Utterance_Embedding_Unit.pdf)
|
| 76 |
|
| 77 |
---
|
| 78 |
|