Instructions to use mispeech/dasheng-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/dasheng-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="mispeech/dasheng-base", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mispeech/dasheng-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"DashengModel"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
| 5 |
"encoder_kwargs": {
|
| 6 |
"depth": 12,
|
| 7 |
"embed_dim": 768,
|
|
@@ -17,9 +20,6 @@
|
|
| 17 |
"target_length": 1008
|
| 18 |
},
|
| 19 |
"loss": "BCELoss",
|
| 20 |
-
"auto_map": {
|
| 21 |
-
"AutoModel": "modeling_dasheng.DashengModel"
|
| 22 |
-
},
|
| 23 |
"model_type": "dasheng",
|
| 24 |
"name": "dasheng-base",
|
| 25 |
"torch_dtype": "float32",
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"DashengModel"
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoModel": "modeling_dasheng.DashengModel"
|
| 7 |
+
},
|
| 8 |
"encoder_kwargs": {
|
| 9 |
"depth": 12,
|
| 10 |
"embed_dim": 768,
|
|
|
|
| 20 |
"target_length": 1008
|
| 21 |
},
|
| 22 |
"loss": "BCELoss",
|
|
|
|
|
|
|
|
|
|
| 23 |
"model_type": "dasheng",
|
| 24 |
"name": "dasheng-base",
|
| 25 |
"torch_dtype": "float32",
|