Automatic Speech Recognition
Transformers
PyTorch
Finnish
wav2vec2
Generated from Trainer
mozilla-foundation/common_voice_7_0
audio
speech
Instructions to use RASMUS/wav2vec2-xlsr-fi-train-aug-bigLM-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RASMUS/wav2vec2-xlsr-fi-train-aug-bigLM-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="RASMUS/wav2vec2-xlsr-fi-train-aug-bigLM-1B")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("RASMUS/wav2vec2-xlsr-fi-train-aug-bigLM-1B") model = AutoModelForCTC.from_pretrained("RASMUS/wav2vec2-xlsr-fi-train-aug-bigLM-1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 262 Bytes
b876eec | 1 2 3 4 5 6 7 8 9 10 11 | {
"do_normalize": true,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"processor_class": "Wav2Vec2ProcessorWithLM",
"return_attention_mask": true,
"sampling_rate": 16000
}
|