{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "stack(): argument 'tensors' (position 1) must be tuple of Tensors, not Tensor",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[2], line 7\u001b[0m\n\u001b[1;32m      4\u001b[0m start_index \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[1;32m      6\u001b[0m semantic_codes_chunk \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mrandint(\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m4000\u001b[39m, (\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m100\u001b[39m))\n\u001b[0;32m----> 7\u001b[0m semantic_codes_chunk \u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstack\u001b[49m\u001b[43m(\u001b[49m\u001b[43msemantic_codes_chunk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# [1, time]\u001b[39;00m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m semantic_skip_factor \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m     11\u001b[0m     mask \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mones_like(semantic_codes_chunk, dtype\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mbool)\n",
      "\u001b[0;31mTypeError\u001b[0m: stack(): argument 'tensors' (position 1) must be tuple of Tensors, not Tensor"
     ]
    }
   ],
   "source": [
    "\n",
    "cond_semantic_n_vocab = 4001\n",
    "semantic_skip_factor = 2\n",
    "semantic_skip_phase = 0\n",
    "start_index = 0\n",
    "\n",
    "semantic_codes_chunk = torch.randint(0, 4000, (1, 100))\n",
    "semantic_codes_chunk\n",
    "\n",
    "if semantic_skip_factor > 1:\n",
    "    mask = torch.ones_like(semantic_codes_chunk, dtype=torch.bool)\n",
    "    indices = (\n",
    "        torch.arange(semantic_codes_chunk.size(1))\n",
    "        + semantic_skip_phase\n",
    "        + start_index\n",
    "    ) % semantic_skip_factor == 0\n",
    "    mask[:, indices] = False\n",
    "    semantic_codes_chunk[mask] = cond_semantic_n_vocab - 1\n",
    "\n",
    "start_index += semantic_codes_chunk.size(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_env",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}