Upload README.md with huggingface_hub

README.md

@@ -104,7 +104,7 @@ LibriSpeech is used here as an independent check on the extent of degradation ca
 Copy/paste to transcribe the first three rows from a HuggingFace dataset with `Trelis/transcribe-en_us-spelling-v1-tiny`:
 
 ```bash
-uv run --with datasets --with transformers --with torchaudio python - <<'PY'
+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
 
@@ -132,7 +132,7 @@ Make sure you have Hugging Face access to both the dataset and model (`huggingfa
 
 **Transcribe your own audio (`/path/to/audio.wav`):**
 ```bash
-uv run --with transformers --with torchaudio python - <<'PY'
+uv run --isolated --with transformers --with 'datasets<3.0' --with soundfile --with librosa --with torchaudio python - <<'PY'
 from transformers import pipeline
 import torchaudio