Instructions to use devanshty/Babel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use devanshty/Babel with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("openai/whisper-large-v3") model = PeftModel.from_pretrained(base_model, "devanshty/Babel") - Notebooks
- Google Colab
- Kaggle
Upload processor_config.json with huggingface_hub
Browse files- processor_config.json +17 -0
processor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor": {
|
| 3 |
+
"chunk_length": 30,
|
| 4 |
+
"dither": 0.0,
|
| 5 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 6 |
+
"feature_size": 128,
|
| 7 |
+
"hop_length": 160,
|
| 8 |
+
"n_fft": 400,
|
| 9 |
+
"n_samples": 480000,
|
| 10 |
+
"nb_max_frames": 3000,
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"padding_value": 0.0,
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
},
|
| 16 |
+
"processor_class": "WhisperProcessor"
|
| 17 |
+
}
|