create_model.py

from transformers import SpeechEncoderDecoderModel, AutoFeatureExtractor, AutoTokenizer, Wav2Vec2Processor

# checkpoints to leverage
encoder_id = "facebook/wav2vec2-xls-r-300m"
decoder_id = "facebook/mbart-large-50"

# load and save speech-encoder-decoder model
# set some hyper-parameters for training and evaluation
model = SpeechEncoderDecoderModel.from_encoder_decoder_pretrained(encoder_id, decoder_id, encoder_add_adapter=True, encoder_feat_proj_dropout=0.0, encoder_layerdrop=0.0, max_length=200, num_beams=5)
model.config.decoder_start_token_id = model.decoder.config.bos_token_id
model.config.pad_token_id = model.decoder.config.pad_token_id
model.config.eos_token_id = model.decoder.config.eos_token_id
model.save_pretrained("./")

# load and save processor
feature_extractor = AutoFeatureExtractor.from_pretrained(encoder_id)
tokenizer = AutoTokenizer.from_pretrained(decoder_id)
processor = Wav2Vec2Processor(feature_extractor, tokenizer)
processor.save_pretrained("./")