Laaj ak tontu ci arsitektu konformer

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Yan ñaari mekaniism la architecture Conformer di boole ci benn blok?
   • Konvolusioŋ ak bàyyi xel ci sa bopp
   • Baamtu ak boole
   • Garab yiy jël dogal ak boole
   • Seetug beam ak tokenisasioŋ
2. Lan moo waral boole convolution ak attention lu am solo la ci wax?
   • Attention mooy yonnee ay detay ci fonem yi ci gox bi, waaye convolution mooy yonnee contexte global bi
   • Convolution dafay jàpp motif yu bërëb bi, fekk bàyyi xel ci sa bopp dafay jàpp contexte bu sori
   • Ñari mbir yooyu yépp ay nataal kese lañu am solo, du audio
   • Kenn ci ñoom du jàppale; gaawaay rek la
3. Lan moy 'Macaron' wala jumtukaayu sandwich bu benn bloku Conformer?
   • Ñaari lalu bàyyi xel ci benn convolution
   • Benn couche feed-forward kese
   • Fàttaliku ak jaxasoo ci diggante ñaari modulu feed-forward yu am xaaju jéego
   • Konvolusioŋ buñ dajale ci kaw konvolusioŋ
4. Ban mbootaay moo dugal Conformer, ak ci ban at?
   • 2018
   • 2015
   • 2012
   • 2020
5. Lan mooy modulu convolution bi ci biir Conformer bi?
   • ab conv ci point, ab GLU, ab conv ci xóotaayu, normalisasioŋ, ak ab aktivasioŋ Swish
   • Benn layer kese lañu boole lépp
   • ab selil LSTM buy dellusi
   • Klasifikatëru àll bu bari
6. On LibriSpeech test-clean/test-other, what WER did the original Conformer paper report with an external language model?
   • 2.1% / 4.3%
   • 1.9% / 3.9%
   • 9.1% / 9.3%
   • 0.1% / 0.3%
7. What positional information does the Conformer paper add to attention?
   • A geographic GPS coordinate for every speech frame
   • A fixed class label for each utterance
   • Relative positional encoding
   • A separate video frame index
8. What word error rates did the Conformer paper report without an external language model on LibriSpeech test/test-other?
   • 20.1% / 40.3%
   • 0.1% / 0.3%
   • 12.1% / 14.3%
   • 2.1% / 4.3%