{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4459c2c1",
   "metadata": {},
   "source": [
    "# Transformers - Example of automatic speech recognition\n",
    "Transformers provides APIs and tools to easily download and train state-of-the-art pretrained models.   \n",
    "Credits: Huggingface documentation and examples "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "eee57435",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "52c02f74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d73869ec68ce4389963d968c2bc0b017",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)lve/main/config.json:   0%|          | 0.00/1.97k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7876afb78def4da887bb2592407fbc21",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading pytorch_model.bin:   0%|          | 0.00/967M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "614e84af1236445d921c4deff744831d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)neration_config.json:   0%|          | 0.00/3.51k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0d41664ca4264e24b695c7c5a942bd62",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)okenizer_config.json:   0%|          | 0.00/842 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9ec43e8f0fc14ebc840fe8899982f3e9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)olve/main/vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6ed828c6658b4d03839d020741a4bd8e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/2.20M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1cc881fa4ddb45c8908f31bc1cf8b158",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)olve/main/merges.txt:   0%|          | 0.00/494k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9ded2a1dc6db4c849c0a698e732ace0f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)main/normalizer.json:   0%|          | 0.00/52.7k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "66463710f31944a39619817b988c2dec",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)in/added_tokens.json:   0%|          | 0.00/2.08k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fc793c7886c849afaecb4c7179d89847",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)cial_tokens_map.json:   0%|          | 0.00/2.08k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "785180b095414d429e378cfafd379fe3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading (…)rocessor_config.json:   0%|          | 0.00/185k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create the transcriber pipeline with GPU\n",
    "transcriber = pipeline(task=\"automatic-speech-recognition\", model=\"openai/whisper-small\", device=0)  # Specify the GPU device index)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "96c282d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "speech_url=\"https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "77ed6cd6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "                <audio  controls=\"controls\" >\n",
       "                    <source src=\"https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac\" type=\"audio/x-flac\" />\n",
       "                    Your browser does not support the audio element.\n",
       "                </audio>\n",
       "              "
      ],
      "text/plain": [
       "<IPython.lib.display.Audio object>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Play th eaudio file\n",
    "import IPython\n",
    "IPython.display.Audio(url=speech_url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96a49da5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Install ffmpeg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c578e043",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%bash\n",
    "wget -O ffmpeg.tar.xz https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz\n",
    "tar xvf ffmpeg.tar.xz"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4c8839a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "path = os.environ['PATH']\n",
    "os.environ['PATH'] += \":./ffmpeg-git-20230313-amd64-static\" # customize the folder name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "82e43a07",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/cvmfs/sft-nightlies.cern.ch/lcg/views/dev4cuda/Mon/x86_64-centos7-gcc11-opt/lib/python3.9/site-packages/transformers/generation/utils.py:1313: UserWarning: Using `max_length`'s default (448) to control the generation length. This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'text': ' I have a dream that one day this nation will rise up and live out the true meaning of its creed.'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transcribe from speech_url\n",
    "transcriber(speech_url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "60b9965a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": 5
}