1. Presentation transcript is a small utility that converts the speech in a video to a text file named transcript.txt. 2. Dependencies pip to set up a venv virtual environment yt-dlp to download the audio from a video stored on the web ffmpeg to convert it to a suitable format for Whisper Whisper to convert the audio to text 3. Initial set up for a given user (to be done only once for each user) ffmpeg, pip and yt-dlp are included in Slint by default. To setup the virtual environment and install Whisper in it, as regular user, type these commands: python3 -m venv ~/.venvs/whisper . ~/.venvs/whisper/bin/activate pip install --upgrade pip pip install faster-whisper" Or just type: /usr/libexec/transcript/setup_whisper 4. Usage: [MODEL_SIZE=] transcript [two letters language] whisper_model can be tiny, base, small, medium or large. The default is small for a good balance of speed and accuracy if you do not have a dedicated GPU. If the language is not set it will be auto-detected. 5. Recommended Whisper model sizes: tiny – fastest, smallest, low accuracy; ideal for quick CPU transcription or low-resource systems. base – fast, slightly more accurate; still very CPU-friendly. small – balanced speed and accuracy; good default for CPU use. medium – high accuracy; slower on CPU, faster on GPU. large – highest accuracy; very slow on CPU, GPU recommended. Rule of thumb: Use tiny/base/small if running on CPU. Use medium/large if you have a GPU and want better accuracy. 6. Supported languages This tool supports all languages provided by OpenAI Whisper. Languages are specified using two-letter ISO 639-1 codes. If no language is specified, the language is automatically detected. The list below comes from OpenAI Whisper. Available languages, listed alphabetically by language name: Afrikaans – af Albanian – sq Amharic – am Arabic – ar Armenian – hy Assamese – as Azerbaijani – az Bashkir – ba Basque – eu Belarusian – be Bengali – bn Bosnian – bs Breton – br Bulgarian – bg Burmese (Myanmar) – my Catalan – ca Chinese – zh Croatian – hr Czech – cs Danish – da Dutch – nl English – en Estonian – et Faroese – fo Finnish – fi French – fr Galician – gl Georgian – ka German – de Greek – el Gujarati – gu Haitian Creole – ht Hausa – ha Hebrew – he Hindi – hi Hungarian – hu Icelandic – is Indonesian – id Italian – it Japanese – ja Javanese – jw Kannada – kn Kazakh – kk Khmer – km Korean – ko Lao – lo Latin – la Latvian – lv Lingala – ln Lithuanian – lt Luxembourgish – lb Macedonian – mk Malagasy – mg Malay – ms Malayalam – ml Maltese – mt Maori – mi Marathi – mr Mongolian – mn Nepali – ne Norwegian – no Norwegian Nynorsk – nn Occitan – oc Pashto – ps Persian – fa Polish – pl Portuguese – pt Punjabi – pa Romanian – ro Russian – ru Sanskrit – sa Serbian – sr Shona – sn Sindhi – sd Sinhala – si Slovak – sk Slovenian – sl Somali – so Spanish – es Sundanese – su Swahili – sw Swedish – sv Tagalog – tl Tajik – tg Tamil – ta Tatar – tt Telugu – te Thai – th Tibetan – bo Turkish – tr Turkmen – tk Ukrainian – uk Urdu – ur Uzbek – uz Vietnamese – vi Welsh – cy Yiddish – yi Yoruba – yo