espnet2.ps2st.qwen2_scorer.Qwen2HFScorer

source

class espnet2.ps2st.qwen2_scorer.Qwen2HFScorer(model, input_ids, attention_mask, input_features=None, feature_attention_mask=None)

Bases: ScorerInterface

final_score(states)

Score eos (optional).

• Parameters:state – Scorer state for prefix tokens
• Returns: final score
• Return type: float

init_state(xs)

Get an initial state for decoding (optional).

• Parameters:x (torch.Tensor) – The encoded feature tensor

Returns: initial state

score(ys, state, xs)

Forward scoring function.

ys: 1D LongTensor of generated tokens so far state: dict with ‘past_kv’ and ‘step’

select_state(states, idx)

Select state with relative ids in the main beam search.

• Parameters:
  • state – Decoder state for prefix tokens
  • i (int) – Index to select a state in the main beam search
  • new_id (int) – New label index to select a state if necessary
• Returns: pruned state
• Return type: state