Update Readme
Browse files
README.md
CHANGED
|
@@ -6,6 +6,11 @@ tags:
|
|
| 6 |
- audio embeddings
|
| 7 |
- convnext-audio
|
| 8 |
- audioset
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
**ConvNeXt-Tiny-AT** is an audio tagging CNN model, trained on **AudioSet** (balanced+unbalanced subsets). It reached 0.471 mAP on the test set.
|
|
@@ -36,7 +41,7 @@ import torchaudio
|
|
| 36 |
|
| 37 |
from audioset_convnext_inf.pytorch.convnext import ConvNeXt
|
| 38 |
|
| 39 |
-
model = ConvNeXt.from_pretrained("topel/ConvNeXt-Tiny-AT", use_auth_token=
|
| 40 |
|
| 41 |
print(
|
| 42 |
"# params:",
|
|
|
|
| 6 |
- audio embeddings
|
| 7 |
- convnext-audio
|
| 8 |
- audioset
|
| 9 |
+
inference: false
|
| 10 |
+
extra_gated_prompt: "The collected information will help acquire a better knowledge of who is using our audio event tools. If relevant, please cite our Interspeech 2023 paper."
|
| 11 |
+
extra_gated_fields:
|
| 12 |
+
Company/university: text
|
| 13 |
+
Website: text
|
| 14 |
---
|
| 15 |
|
| 16 |
**ConvNeXt-Tiny-AT** is an audio tagging CNN model, trained on **AudioSet** (balanced+unbalanced subsets). It reached 0.471 mAP on the test set.
|
|
|
|
| 41 |
|
| 42 |
from audioset_convnext_inf.pytorch.convnext import ConvNeXt
|
| 43 |
|
| 44 |
+
model = ConvNeXt.from_pretrained("topel/ConvNeXt-Tiny-AT", use_auth_token="ACCESS_TOKEN_GOES_HERE", map_location='cpu')
|
| 45 |
|
| 46 |
print(
|
| 47 |
"# params:",
|