{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2024-06-25 20:01:43,998] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[2024-06-25 20:01:44,318] torch.distributed.elastic.multiprocessing.redirects: [WARNING] NOTE: Redirects are currently not supported in Windows or MacOs.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading model...\n",
      "[2024-06-25 20:02:01,663] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.14.0+ce78a63, git-hash=ce78a63, git-branch=master\n",
      "[2024-06-25 20:02:01,664] [WARNING] [config_utils.py:69:_process_deprecated_field] Config parameter replace_method is deprecated. This parameter is no longer needed, please remove from your call to DeepSpeed-inference\n",
      "[2024-06-25 20:02:01,665] [WARNING] [config_utils.py:69:_process_deprecated_field] Config parameter mp_size is deprecated use tensor_parallel.tp_size instead\n",
      "[2024-06-25 20:02:01,666] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1\n",
      "[2024-06-25 20:02:01,900] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 1024, 'intermediate_size': 4096, 'heads': 16, 'num_hidden_layers': -1, 'dtype': torch.float32, 'pre_layer_norm': True, 'norm_type': <NormType.LayerNorm: 1>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': -1, 'rotate_half': False, 'rotate_every_two': True, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GELU: 1>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000}\n"
     ]
    }
   ],
   "source": [
    "from models.TTS_utils import load_manual_xtts_v2\n",
    "config_path = \"test/config.json\"\n",
    "model_path = \"test\"\n",
    "\n",
    "xtts_v2_model = load_manual_xtts_v2(config_path, model_path)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Inference...\n",
      "No more text to process\n",
      "Inference...\n",
      "No more text to process\n"
     ]
    }
   ],
   "source": [
    "from models.TTS_utils import stream_prod\n",
    "stream_prod(xtts_v2_model, \"record_temp.json\", \"audio_segments/\")\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "capstone",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}