Feature Extraction
sentence-transformers
Safetensors
qwen2_5_omni_thinker
voice
speech
emotion
audio-text
clap
contrastive
lora
prototypical-contrastive
Instructions to use laion/voiceclap-large-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use laion/voiceclap-large-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("laion/voiceclap-large-v2") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
License: mark non-commercial restriction from CC BY-NC training data (Expresso)
#2
by gijs - opened
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
| 3 |
pipeline_tag: feature-extraction
|
| 4 |
library_name: sentence-transformers
|
| 5 |
tags:
|
|
@@ -91,4 +92,4 @@ score = (audio_emb @ text_emb.T).item()
|
|
| 91 |
|
| 92 |
## License
|
| 93 |
|
| 94 |
-
Apache-2.0
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: apache-2.0-non-commercial-restriction
|
| 4 |
pipeline_tag: feature-extraction
|
| 5 |
library_name: sentence-transformers
|
| 6 |
tags:
|
|
|
|
| 92 |
|
| 93 |
## License
|
| 94 |
|
| 95 |
+
Apache-2.0 base model + non-commercial restriction due to CC BY-NC training data (e.g. Expresso).
|