Update modelscope_models.md

Chong Zhang

2023-05-23 5fec3c9e58fceda85fa2daf7deec2492372dac8a

 funasr/models/encoder/sanm_encoder.py

@@ -6,12 +6,14 @@
import logging
import torch
import torch.nn as nn
import torch.nn.functional as F
from funasr.modules.streaming_utils.chunk_utilis import overlap_chunk
from typeguard import check_argument_types
import numpy as np
from funasr.torch_utils.device_funcs import to_device
from funasr.modules.nets_utils import make_pad_mask
from funasr.modules.attention import MultiHeadedAttention, MultiHeadedAttentionSANM, MultiHeadedAttentionSANMwithMask
from funasr.modules.embedding import SinusoidalPositionEncoder
from funasr.modules.embedding import SinusoidalPositionEncoder, StreamSinusoidalPositionEncoder
from funasr.modules.layer_norm import LayerNorm
from funasr.modules.multi_layer_conv import Conv1dLinear
from funasr.modules.multi_layer_conv import MultiLayeredConv1d
@@ -25,9 +27,10 @@
from funasr.modules.subsampling import Conv2dSubsampling8
from funasr.modules.subsampling import TooShortUttError
from funasr.modules.subsampling import check_short_utt
from funasr.modules.mask import subsequent_mask, vad_mask

from funasr.models.ctc import CTC
from funasr.models.encoder.abs_encoder import AbsEncoder
from funasr.modules.mask import subsequent_mask, vad_mask

class EncoderLayerSANM(nn.Module):
    def __init__(
@@ -117,7 +120,7 @@

class SANMEncoder(AbsEncoder):
    """
    author: Speech Lab, Alibaba Group, China
    Author: Speech Lab of DAMO Academy, Alibaba Group
    San-m: Memory equipped self-attention for end-to-end speech recognition
    https://arxiv.org/abs/2006.01713

@@ -180,6 +183,8 @@
                self.embed = torch.nn.Linear(input_size, output_size)
        elif input_layer == "pe":
            self.embed = SinusoidalPositionEncoder()
        elif input_layer == "pe_online":
            self.embed = StreamSinusoidalPositionEncoder()
        else:
            raise ValueError("unknown input_layer: " + input_layer)
        self.normalize_before = normalize_before
@@ -347,6 +352,14 @@
            return (xs_pad, intermediate_outs), olens, None
        return xs_pad, olens, None

    def _add_overlap_chunk(self, feats: np.ndarray, cache: dict = {}):
        if len(cache) == 0:
            return feats
        cache["feats"] = to_device(cache["feats"], device=feats.device)
        overlap_feats = torch.cat((cache["feats"], feats), dim=1)
        cache["feats"] = overlap_feats[:, -(cache["chunk_size"][0] + cache["chunk_size"][2]):, :]
        return overlap_feats

    def forward_chunk(self,
                      xs_pad: torch.Tensor,
                      ilens: torch.Tensor,
@@ -357,8 +370,11 @@
        if self.embed is None:
            xs_pad = xs_pad
        else:
            xs_pad = self.embed.forward_chunk(xs_pad, cache)

            xs_pad = self.embed(xs_pad, cache)
        if cache["tail_chunk"]:
            xs_pad = to_device(cache["feats"], device=xs_pad.device)
        else:
            xs_pad = self._add_overlap_chunk(xs_pad, cache)
        encoder_outs = self.encoders0(xs_pad, None, None, None, None)
        xs_pad, masks = encoder_outs[0], encoder_outs[1]
        intermediate_outs = []
@@ -549,7 +565,7 @@

class SANMEncoderChunkOpt(AbsEncoder):
    """
    author: Speech Lab, Alibaba Group, China
    Author: Speech Lab of DAMO Academy, Alibaba Group
    SCAMA: Streaming chunk-aware multihead attention for online end-to-end speech recognition
    https://arxiv.org/abs/2006.01713

@@ -962,7 +978,7 @@

class SANMVadEncoder(AbsEncoder):
    """
    author: Speech Lab, Alibaba Group, China
    Author: Speech Lab of DAMO Academy, Alibaba Group

    """