Instructions to use mispeech/ced-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/ced-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="mispeech/ced-mini", trust_remote_code=True)# Load model directly from transformers import AutoModelForAudioClassification model = AutoModelForAudioClassification.from_pretrained("mispeech/ced-mini", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -26,8 +26,7 @@ Notable differences from other available models include:
|
|
| 26 |
1. Performance: CED with 10M parameters outperforms the majority of previous approaches (~80M).
|
| 27 |
|
| 28 |
### Model Sources
|
| 29 |
-
- **
|
| 30 |
-
- **Repository:** https://github.com/jimbozhang/hf_transformers_custom_model_ced
|
| 31 |
- **Paper:** [CED: Consistent ensemble distillation for audio tagging](https://arxiv.org/abs/2308.11957)
|
| 32 |
- **Demo:** https://huggingface.co/spaces/mispeech/ced-base
|
| 33 |
|
|
|
|
| 26 |
1. Performance: CED with 10M parameters outperforms the majority of previous approaches (~80M).
|
| 27 |
|
| 28 |
### Model Sources
|
| 29 |
+
- **Repository:** https://github.com/RicherMans/CED
|
|
|
|
| 30 |
- **Paper:** [CED: Consistent ensemble distillation for audio tagging](https://arxiv.org/abs/2308.11957)
|
| 31 |
- **Demo:** https://huggingface.co/spaces/mispeech/ced-base
|
| 32 |
|