How to use TheRamsay/wav2vec2-ctc-scratch-50M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="TheRamsay/wav2vec2-ctc-scratch-50M")
# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("TheRamsay/wav2vec2-ctc-scratch-50M") model = AutoModelForCTC.from_pretrained("TheRamsay/wav2vec2-ctc-scratch-50M")
5016bfd 0b9480c 5016bfd
1
2
3
4
5
6
7
8
9
10
11
{ "do_normalize": true, "feature_dim": 1, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0.0, "return_attention_mask": true, "sampling_rate": 16000 }
