Instructions to use enactic/avista-base-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use enactic/avista-base-plus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="enactic/avista-base-plus", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("enactic/avista-base-plus", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "feature_extraction_avhubert.AVHubertFeatureExtractor", | |
| "AutoProcessor": "processing_avhubert.AVHubertProcessor" | |
| }, | |
| "feature_extractor_type": "AVHubertFeatureExtractor", | |
| "image_crop_size": 88, | |
| "landmark_indices": [ | |
| 5, | |
| 411, | |
| 199, | |
| 187 | |
| ], | |
| "max_sample_size": null, | |
| "min_detection_confidence": 0.5, | |
| "min_tracking_confidence": 0.5, | |
| "normalize": true, | |
| "processor_class": "AVHubertProcessor", | |
| "refine_landmarks": false, | |
| "sr": 16000, | |
| "stack_order_audio": 4, | |
| "static_image_mode": false, | |
| "transforms": [ | |
| { | |
| "training": "True", | |
| "transforms_type": "ToImage" | |
| }, | |
| { | |
| "size": "(88, 88)", | |
| "training": "True", | |
| "transforms_type": "CenterCrop" | |
| }, | |
| { | |
| "dtype": "torch.float32", | |
| "scale": "True", | |
| "training": "True", | |
| "transforms_type": "ToDtype" | |
| }, | |
| { | |
| "inplace": "False", | |
| "mean": "[0.421]", | |
| "std": "[0.165]", | |
| "training": "True", | |
| "transforms_type": "Normalize" | |
| } | |
| ] | |
| } | |