model_name_or_path = "openai/whisper-large-v3"
task = "transcribe"
import json
import os
from transformers import WhisperFeatureExtractor
from transformers import WhisperTokenizer

feature_extractor = WhisperFeatureExtractor.from_pretrained(model_name_or_path)
tokenizer = WhisperTokenizer.from_pretrained(model_name_or_path, task=task)


from peft import PeftModel, PeftConfig
from transformers import WhisperForConditionalGeneration, Seq2SeqTrainer

peft_model_id = "flurin17/whisper-large-v3-peft-swiss-german" # Use the same model ID as before.
peft_config = PeftConfig.from_pretrained(peft_model_id)
model = WhisperForConditionalGeneration.from_pretrained(
    peft_config.base_model_name_or_path, load_in_8bit=True, device_map="auto"
)
model = PeftModel.from_pretrained(model, peft_model_id)
model.config.use_cache = True


from transformers import AutomaticSpeechRecognitionPipeline
import torch
pipe = AutomaticSpeechRecognitionPipeline(model=model, tokenizer=tokenizer, feature_extractor=feature_extractor)

with torch.cuda.amp.autocast():
    result = pipe(r"L:\random\audio.mp3", generate_kwargs={"language": "german"})
print(result["text"])