How to use jsnfly/wav2vec2-large-xlsr-53-german-gpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jsnfly/wav2vec2-large-xlsr-53-german-gpt2")
# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("jsnfly/wav2vec2-large-xlsr-53-german-gpt2") model = AutoModelForSpeechSeq2Seq.from_pretrained("jsnfly/wav2vec2-large-xlsr-53-german-gpt2")
SFconvertbot