How to use Edresson/wav2vec2-large-100k-voxpopuli-ft-TTS-Dataset-plus-data-augmentation-russian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Edresson/wav2vec2-large-100k-voxpopuli-ft-TTS-Dataset-plus-data-augmentation-russian")
# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Edresson/wav2vec2-large-100k-voxpopuli-ft-TTS-Dataset-plus-data-augmentation-russian") model = AutoModelForCTC.from_pretrained("Edresson/wav2vec2-large-100k-voxpopuli-ft-TTS-Dataset-plus-data-augmentation-russian")
SFconvertbot