Automatic Speech Recognition
PEFT
Safetensors
Transformers
English
lora
singapore
education
speech
nmlp
Instructions to use munyew/meralion-education-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use munyew/meralion-education-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("C:/Projects/meralion-server/models/meralion_2_3b") model = PeftModel.from_pretrained(base_model, "munyew/meralion-education-lora") - Transformers
How to use munyew/meralion-education-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="munyew/meralion-education-lora")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("munyew/meralion-education-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_meralion2.MERaLiON2Processor" | |
| }, | |
| "do_normalize": true, | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_meralion2.MERaLiON2Processor" | |
| }, | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| }, | |
| "fixed_speech_embeds_length": 100, | |
| "processor_class": "MERaLiON2Processor", | |
| "speech_token_index": 255999, | |
| "time_duration_limit": 300, | |
| "whisper_chunk_size": 30 | |
| } | |