Fixed bugs with latest transformers.

README.md

@@ -68,10 +68,10 @@ for message in conversation:
                     sr=processor.feature_extractor.sampling_rate)[0]
                 )
 
-inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
-inputs.input_ids = inputs.input_ids.to("cuda")
+inputs = processor(text=text, audio=audios, return_tensors="pt", padding=True)
+inputs = inputs.to("cuda")
 
-generate_ids = model.generate(**inputs, max_length=256)
+generate_ids = model.generate(**inputs, max_new_tokens=256)
 generate_ids = generate_ids[:, inputs.input_ids.size(1):]
 
 response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
@@ -116,10 +116,10 @@ for message in conversation:
                         sr=processor.feature_extractor.sampling_rate)[0]
                 )
 
-inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
-inputs.input_ids = inputs.input_ids.to("cuda")
+inputs = processor(text=text, audio=audios, return_tensors="pt", padding=True)
+inputs = inputs.to("cuda")
 
-generate_ids = model.generate(**inputs, max_length=256)
+generate_ids = model.generate(**inputs, max_new_tokens=256)
 generate_ids = generate_ids[:, inputs.input_ids.size(1):]
 
 response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
@@ -171,11 +171,11 @@ for conversation in conversations:
                             sr=processor.feature_extractor.sampling_rate)[0]
                     )
 
-inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
+inputs = processor(text=text, audio=audios, return_tensors="pt", padding=True)
 inputs['input_ids'] = inputs['input_ids'].to("cuda")
-inputs.input_ids = inputs.input_ids.to("cuda")
+inputs = inputs.to("cuda")
 
-generate_ids = model.generate(**inputs, max_length=256)
+generate_ids = model.generate(**inputs, max_new_tokens=256)
 generate_ids = generate_ids[:, inputs.input_ids.size(1):]
 
 response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)