Create README.md

README.md

@@ -0,0 +1,27 @@
+```python=
+import nlp2
+import json
+from datasets import load_dataset
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from asrp.code2voice_model.hubert import hifigan_hubert_layer6_code100
+import IPython.display as ipd
+
+tokenizer = AutoTokenizer.from_pretrained("Oscarshih/long-t5-base-SQA-15ep")
+model = AutoModelForSeq2SeqLM.from_pretrained("Oscarshih/long-t5-base-SQA-15ep")
+dataset = load_dataset("voidful/NMSQA-CODE")
+cs = hifigan_hubert_layer6_code100()
+
+qa_item = dataset['dev'][0]
+question_unit = json.loads(qa_item['hubert_100_question_unit'])[0]["merged_code"]
+context_unit = json.loads(qa_item['hubert_100_context_unit'])[0]["merged_code"]
+answer_unit = json.loads(qa_item['hubert_100_answer_unit'])[0]["merged_code"]
+
+# groundtruth answer
+ipd.Audio(data=cs(answer_unit), autoplay=False, rate=cs.sample_rate)
+
+# predict answer
+inputs = tokenizer("".join([f"v_tok_{i}" for i in question_unit]) + "".join([f"v_tok_{i}" for i in context_unit]), return_tensors="pt")
+code = tokenizer.batch_decode(model.generate(**inputs,max_length=1024))[0]
+code = [int(i) for i in code.replace("</s>","").replace("<s>","").split("v_tok_")[1:]]
+ipd.Audio(data=cs(code), autoplay=False, rate=cs.sample_rate)
+```