whisper

install.packages("whisper")

remotes::install_github("cornball-ai/whisper")

library(whisper)

# Transcribe the bundled JFK "Ask not" speech (prompts to download model on first use)
jfk <- system.file("audio", "jfk.mp3", package = "whisper")
result <- transcribe(jfk)
result$text
#> "Ask not what your country can do for you, ask what you can do for your country."

Download 'tiny' model (~151 MB) from HuggingFace? (Yes/no/cancel)

# Download a model explicitly
download_whisper_model("tiny")

# List available models
list_whisper_models()
#> [1] "tiny" "base" "small" "medium" "large-v3"

# Check which models are downloaded
list_downloaded_models()

# Check if a specific model exists locally
model_exists("tiny")

# Basic transcription
result <- transcribe("audio.wav")
print(result$text)

# Specify model size
result <- transcribe("audio.wav", model = "small")

# Force CPU (useful if CUDA has issues)
result <- transcribe("audio.wav", device = "cpu")

# Non-English audio (specify language for better accuracy)
allende <- system.file("audio", "allende.mp3", package = "whisper")
result <- transcribe(allende, language = "es")

# Translate to English (quality is model-dependent; larger models work better)
result <- transcribe(allende, task = "translate", language = "es", model = "small")