https://bnmy6581.tistory.com/133 --(1) [Whisper] Robust Speech Recognition via Large-Scale Weak Supervision - (1) bnmy6581.tistory.com https://bnmy6581.tistory.com/134 --(2) [Whisper] Robust Speech Recognition via Large-Scale Weak Supervision - (2) https://bnmy6581.tistory.com/133 --(1) [Whisper] Robust Speech Recognition via Large-Scale Weak Supervision - (1) bnmy6581.tistory.com https://arxiv...

https://bnmy6581.tistory.com/133 --(1) [Whisper] Robust Speech Recognition via Large-Scale Weak Supervision - (1) bnmy6581.tistory.com https://arxiv.org/abs/2109.07740 Scaling Laws for Neural Machine Translation We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of model..

LeetCode-2 Add Two Numbers : Add Two Numbers in Linked List note : You may assume the two numbers do not contain any leading zero, except the number 0 itself.myAnswer :::python #Definition for singly-linked list. class ListNode: def init(self, val=0, next=None): self.val = val self.next = next class Solution: def addTwoNumbers(self, l1: Optional[ListNode], l2: Optional[ListNode]) -> Optional[Lis..

LeetCode-206 Reverse Linked List : Reverse Linked List note : 연결 리스트 역순으로 정렬 :::python # Definition for singly-linked list. # class ListNode: # def init(self, val=0, next=None): # self.val = val # self.next = next class Solution: def reverseList(self, head: Optional[ListNode]) -> Optional[ListNode]: def reverse(node: ListNode, prev: ListNode = None): if not node: return prev next, node.next = no..

Robust Speech Recognition via Large-Scale Weak Supervision *large model은 2023.1 large-v2와 동일하게 바뀜 KsponSpeech 데이터는 짧은 발화의 audio를 주로 구성되어있다. Whisper는 99개의 토큰으로 처음 발화에 대한 언어 예측(language identification)을 수행한다. 하지만 너무 짧은 발화 같은 경우 whisper가 다른 언어로 예측해 translate 자체가 틀려버려 CER이 증가하는 것을 볼 수 있다. language Configure을 korean으로 설정하면 language identification을 수행하지 않고 바로 transcript로 예측해 더 좋은 성과가 났다. model size는 예..