Instructions to use enactic/avista-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use enactic/avista-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="enactic/avista-base", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("enactic/avista-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +3 -1
preprocessor_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
-
"AutoFeatureExtractor": "feature_extraction_avhubert.AVHubertFeatureExtractor"
|
|
|
|
| 4 |
},
|
| 5 |
"feature_extractor_type": "AVHubertFeatureExtractor",
|
| 6 |
"image_crop_size": 88,
|
|
@@ -14,6 +15,7 @@
|
|
| 14 |
"min_detection_confidence": 0.5,
|
| 15 |
"min_tracking_confidence": 0.5,
|
| 16 |
"normalize": true,
|
|
|
|
| 17 |
"refine_landmarks": false,
|
| 18 |
"sr": 16000,
|
| 19 |
"stack_order_audio": 4,
|
|
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
+
"AutoFeatureExtractor": "feature_extraction_avhubert.AVHubertFeatureExtractor",
|
| 4 |
+
"AutoProcessor": "processing_avhubert.AVHubertProcessor"
|
| 5 |
},
|
| 6 |
"feature_extractor_type": "AVHubertFeatureExtractor",
|
| 7 |
"image_crop_size": 88,
|
|
|
|
| 15 |
"min_detection_confidence": 0.5,
|
| 16 |
"min_tracking_confidence": 0.5,
|
| 17 |
"normalize": true,
|
| 18 |
+
"processor_class": "AVHubertProcessor",
|
| 19 |
"refine_landmarks": false,
|
| 20 |
"sr": 16000,
|
| 21 |
"stack_order_audio": 4,
|