from transformers import WhisperForConditionalGeneration, WhisperTokenizer, WhisperProcessor
from peft import PeftModel

tokenizer = WhisperTokenizer.from_pretrained("openai/whisper-large-v2", task="transcribe")
tokenizer.add_special_tokens({"additional_special_tokens": ["<|ip|>"] + tokenizer.all_special_tokens})

base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2")
base_model.generation_config.lang_to_id["<|ip|>"] = tokenizer.convert_tokens_to_ids(["<|ip|>"])[0]
base_model.resize_token_embeddings(len(tokenizer))

whipa_model = PeftModel.from_pretrained(base_model, "jshrdt/lowhipa-large-cv")

whipa_model.generation_config.language = "<|ip|>"
whipa_model.generation_config.task = "transcribe"

whipa_processor = WhisperProcessor.from_pretrained("openai/whisper-large-v2", task="transcribe")