voidful/tts_hubert_cluster_bart_base

1---2language: en3datasets:4- librispeech5tags:6- audio7- automatic-speech-recognition8- speech9- asr10- hubert11license: apache-2.012metrics:13- wer14- cer15---16 17# voidful/tts_hubert_cluster_bart_base18 19 20## Usage21````python22from transformers import AutoTokenizer, AutoModelForSeq2SeqLM23tokenizer = AutoTokenizer.from_pretrained("voidful/tts_hubert_cluster_bart_base")24model = AutoModelForSeq2SeqLM.from_pretrained("voidful/tts_hubert_cluster_bart_base")25````26generate output27```python28gen_output = model.generate(input_ids=tokenizer("going along slushy country roads and speaking to damp audience in drifty school rooms day after day for a fortnight he'll have to put in an appearance at some place of worship on sunday morning and he can come to ask immediately afterwards",return_tensors='pt').input_ids, max_length=1024)29print(tokenizer.decode(gen_output[0], skip_special_tokens=True))30```31 32## Result33`:vtok402::vtok329::vtok329::vtok75::vtok75::vtok75::vtok44::vtok150::vtok150::vtok222::vtok280::vtok280::vtok138::vtok409::vtok409::vtok409::vtok46::vtok441:`