Instructions to use cdactvm/kannada_w2v-bert_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cdactvm/kannada_w2v-bert_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="cdactvm/kannada_w2v-bert_model")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("cdactvm/kannada_w2v-bert_model") model = AutoModelForCTC.from_pretrained("cdactvm/kannada_w2v-bert_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 277 Bytes
0384a25 | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
"feature_size": 80,
"num_mel_bins": 80,
"padding_side": "right",
"padding_value": 0.0,
"processor_class": "Wav2Vec2BertProcessor",
"return_attention_mask": true,
"sampling_rate": 16000,
"stride": 2
}
|