Automatic Speech Recognition
Transformers
Safetensors
Malagasy
wav2vec2-bert
speech
malagasy
madagascar
w2v-bert-2.0
ctc
low-resource
african-languages
Eval Results (legacy)
Instructions to use Flo976/w2v-bert-malagasy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Flo976/w2v-bert-malagasy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Flo976/w2v-bert-malagasy")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Flo976/w2v-bert-malagasy") model = AutoModelForCTC.from_pretrained("Flo976/w2v-bert-malagasy", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 275 Bytes
7c22c3b | 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": 1,
"processor_class": "Wav2Vec2BertProcessor",
"return_attention_mask": true,
"sampling_rate": 16000,
"stride": 2
}
|