fix: --ignore-requires-python for omnilingual-asr 0.2.0 on Python 3.12

README.md

@@ -95,8 +95,10 @@ FP16 and FP32 produce **identical transcripts**, so FP16 is the recommended defa
 # system dependency for audio I/O
 sudo apt-get install -y libsndfile1   # (Linux)  /  brew install libsndfile (macOS)
 
-# pin 0.2.0 — earlier versions don't register the 3b_v2 architecture this model needs
-pip install omnilingual-asr==0.2.0 huggingface_hub
+# Need omnilingual-asr 0.2.0 (it registers the 3b_v2 architecture this model uses).
+# --ignore-requires-python: 0.2.0's metadata caps python at "<=3.12" (read as <=3.12.0), which
+# wrongly excludes Python 3.12.x (e.g. Colab). The flag installs it anyway; it runs fine on 3.12.
+pip install --ignore-requires-python omnilingual-asr==0.2.0 huggingface_hub
 # Pin the whole torch stack to the CUDA 12.8 build that fairseq2 needs.
 # (Without this you hit `libcudart.so.13` / torchvision::nms errors from a mismatched torchaudio/torchvision.)
 pip install torch==2.8.0 torchaudio==2.8.0 torchvision==0.23.0 --index-url https://download.pytorch.org/whl/cu128