learn.ifs.name

PUMA: language tokens for low-resource multilingual ASR

Oukid et al., 2026, PUMA (Findings of ACL 2026)

Subscriber deck — free during early access

4 cards in “4.1–4.2 Data & setup” · whole deck

4.1–4.2 Data & setup

  1. Which ten languages does PUMA evaluate on?
    Kabyle, Wolof, Hausa, Yoruba, Igbo, Shona, Xhosa, Fon, Twi, and Arabic.
    • Oukid et al., 2026, PUMA (Findings of ACL 2026), §4.1, p. 375
  2. How much training data per language, at what sampling rate, and with what output vocabulary?
    About 15 hours of transcribed speech per language on average, resampled to 16 kHz. The character sets are merged into one shared vocabulary of 204 characters.
    • Oukid et al., 2026, PUMA (Findings of ACL 2026), §4.1, p. 375
  3. Key PUMA hyperparameters?
    AdamW, learning rate \(10^{-3}\), weight decay \(10^{-3}\), effective batch size 32 (via gradient accumulation). ULP: 4 Transformer blocks, hidden dimension 768, 8 heads, projection dimension 1280. One NVIDIA A100 80 GB.
    • Oukid et al., 2026, PUMA (Findings of ACL 2026), §4.2, p. 375
  4. Which evaluation metrics does PUMA report?
    WER (primary), plus BLEU and ROUGE-1/2/L, which measure n-gram overlap between hypothesis and reference.

Sources