app.py

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "openai/whisper-large-v3"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=False, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)
result = pipe("/content/BryanThe_Ideal_Republic.ogg", generate_kwargs={"language": "french"})
print(result["text"]) # transcritpion
print(result["chunks"]) # translation

from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration


tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
retriever = RagRetriever.from_pretrained("facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True)
rag_model = RagSequenceForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever)

def retrieve_and_generate_response(transcribed_text):
    # Tokenize the transcribed text
    input_ids = tokenizer(transcribed_text, return_tensors="pt").input_ids

    # Generate response
    outputs = rag_model.generate(input_ids)
    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]

    return response

response = retrieve_and_generate_response(result["text"])
print("Response:", response)