in whisper/decoding.py [0:0]
def rank(self, tokens: List[List[Tensor]], sum_logprobs: List[List[float]]):
def scores(logprobs, lengths):
result = []
for logprob, length in zip(logprobs, lengths):
if self.length_penalty is None:
penalty = length
else:
# from the Google NMT paper
penalty = ((5 + length) / 6) ** self.length_penalty
result.append(logprob / penalty)
return result
# get the sequence with the highest score
lengths = [[len(t) for t in s] for s in tokens]
return [np.argmax(scores(p, l)) for p, l in zip(sum_logprobs, lengths)]