Feature Extraction
Transformers
Safetensors
meralion_bestrq
speech
best-rq
meralion
meralion-2
custom_code
Instructions to use MERaLiON/MERaLiON-SpeechEncoder-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MERaLiON/MERaLiON-SpeechEncoder-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="MERaLiON/MERaLiON-SpeechEncoder-2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MERaLiON/MERaLiON-SpeechEncoder-2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "processing_bestrq_conformer.ModifiedWhisperFeatureExtractor", | |
| "AutoProcessor": "processing_bestrq_conformer.ModifiedWhisperFeatureExtractor" | |
| }, | |
| "chunk_length": 120, | |
| "feature_extractor_type": "ModifiedWhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 1920000, | |
| "nb_max_frames": 12000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |