export

游雁

2023-03-31 4ba1011b42e041ee1d71448eefd7ef2e7bd61bb6

 funasr/export/models/vad_realtime_transformer.py

@@ -1,17 +1,12 @@
from typing import Any
from typing import List
from typing import Tuple

import torch
import torch.nn as nn

from funasr.modules.embedding import SinusoidalPositionEncoder
from funasr.punctuation.sanm_encoder import SANMVadEncoder as Encoder
from funasr.punctuation.abs_model import AbsPunctuation
from funasr.punctuation.sanm_encoder import SANMVadEncoder
from funasr.models.encoder.sanm_encoder import SANMVadEncoder
from funasr.export.models.encoder.sanm_encoder import SANMVadEncoder as SANMVadEncoder_export

class VadRealtimeTransformer(AbsPunctuation):
class VadRealtimeTransformer(nn.Module):

    def __init__(
        self,
@@ -32,11 +27,15 @@
            assert False, "Only support samn encode."
        # self.encoder = model.encoder
        self.decoder = model.decoder
        self.model_name = model_name



    def forward(self, input: torch.Tensor, text_lengths: torch.Tensor,
                vad_indexes: torch.Tensor) -> Tuple[torch.Tensor, None]:
    def forward(self, input: torch.Tensor,
                text_lengths: torch.Tensor,
                vad_indexes: torch.Tensor,
                sub_masks: torch.Tensor,
                ) -> Tuple[torch.Tensor, None]:
        """Compute loss value from buffer sequences.

        Args:
@@ -46,7 +45,7 @@
        """
        x = self.embed(input)
        # mask = self._target_mask(input)
        h, _, _ = self.encoder(x, text_lengths, vad_indexes)
        h, _ = self.encoder(x, text_lengths, vad_indexes, sub_masks)
        y = self.decoder(h)
        return y

@@ -57,11 +56,13 @@
        length = 120
        text_indexes = torch.randint(0, self.embed.num_embeddings, (1, length))
        text_lengths = torch.tensor([length], dtype=torch.int32)
        vad_mask = torch.ones(length, length)[None, None, :, :]
        return (text_indexes, text_lengths, vad_mask)
        vad_mask = torch.ones(length, length, dtype=torch.float32)[None, None, :, :]
        sub_masks = torch.ones(length, length, dtype=torch.float32)
        sub_masks = torch.tril(sub_masks).type(torch.float32)
        return (text_indexes, text_lengths, vad_mask, sub_masks[None, None, :, :])

    def get_input_names(self):
        return ['input', 'text_lengths', 'vad_mask']
        return ['input', 'text_lengths', 'vad_mask', 'sub_masks']

    def get_output_names(self):
        return ['logits']
@@ -71,6 +72,14 @@
            'input': {
                1: 'feats_length'
            },
            'vad_mask': {
                2: 'feats_length1',
                3: 'feats_length2'
            },
            'sub_masks': {
                2: 'feats_length1',
                3: 'feats_length2'
            },
            'logits': {
                1: 'logits_length'
            },