atiorh

# !pip install transformers sentencepiece

import torch
import torch.nn as nn
torch.set_grad_enabled(False)

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.activations import ReLUSquaredActivation

from collections import defaultdict, OrderedDict

atiorh

let pipe = try await WhisperKit(model: "large-v3")
let result = try await pipe.transcribe(audioPath: "test.{wav/flac/mp3}")?.text