Rolv-Arild
/

xls-r-300m-npsc-seq2seq

Automatic Speech Recognition Transformers PyTorch TensorBoard speech-encoder-decoder generated_from_trainer Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

xls-r-300m-npsc-seq2seq / create_model.py

Rolv-Arild's picture

Training in progress, step 400

3308cff about 2 years ago

raw history blame contribute delete

No virus

1.12 kB

	#!/usr/bin/env python3
	from transformers import SpeechEncoderDecoderModel, AutoFeatureExtractor, AutoTokenizer
	import torch


	encoder_id = "facebook/wav2vec2-xls-r-300m"
	decoder_id = "facebook/bart-large"

	model = SpeechEncoderDecoderModel.from_encoder_decoder_pretrained(encoder_id, decoder_id, encoder_add_adapter=True)
	model.config.encoder.feat_proj_dropout = 0.0
	model.config.encoder.final_dropout = 0.0
	model.config.encoder.mask_time_prob = 0.1
	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.config.max_length = 200
	model.config.num_beams = 5
	model.config.encoder.layerdrop = 0.0
	model.config.use_cache = False
	model.config.processor_class = "Wav2Vec2Processor"

	# check if generation works
	out = model.generate(torch.ones((1, 2000)))

	model.save_pretrained("./")

	feature_etxractor = AutoFeatureExtractor.from_pretrained(encoder_id)
	feature_etxractor.save_pretrained("./")
	tokenizer = AutoTokenizer.from_pretrained(decoder_id)
	tokenizer.save_pretrained("./")