transcribe-en_us-spelling-v1-tiny-ctranslate2

uv run --isolated --with transformers --with 'datasets<3.0' --with soundfile --with librosa --with torchaudio python - <<'PY'
from datasets import load_dataset
from transformers import pipeline

DATASET_ID = "Trelis/transcribe-to-en_GB-v1"
MODEL_ID = "Trelis/transcribe-en_us-spelling-v1-tiny-ctranslate2"

print(f"Loading dataset: {DATASET_ID} (first 3 rows)")
dataset = load_dataset(DATASET_ID, split="test[:3]")

print(f"Loading ASR model: {MODEL_ID}")
asr = pipeline("automatic-speech-recognition", model=MODEL_ID, return_timestamps="word")

for idx, sample in enumerate(dataset):
    audio = sample["audio"]
    transcription = asr(
        {"array": audio["array"], "sampling_rate": audio["sampling_rate"]}
    )
    print(f"\nSample {idx + 1}")
    print(f"  Reference: {sample.get('text')}")
    print(f"  Transcript: {transcription['text']}")
PY

# Preview rendered files in model_info/generated_readmes/
uv run --with pyyaml --with huggingface_hub python model_info/push_readmes.py

# Push READMEs to HuggingFace Hub (requires huggingface-cli login)
uv run --with pyyaml --with huggingface_hub python model_info/push_readmes.py --push