mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
shfit to shift (#2266)
This commit is contained in:
Rin Arakaki
GitHub
parent
ae7aff2e9c
commit
1367973f98
@ -5,13 +5,13 @@
|
||||
The original intention of the funasr-1.x.x version is to make model integration easier. The core feature is the registry and AutoModel:
|
||||
|
||||
* The introduction of the registry enables the development of building blocks to access the model, compatible with a variety of tasks;
|
||||
|
||||
|
||||
* The newly designed AutoModel interface unifies modelscope, huggingface, and funasr inference and training interfaces, and supports free download of repositories;
|
||||
|
||||
|
||||
* Support model export, demo-level service deployment, and industrial-level multi-concurrent service deployment;
|
||||
|
||||
|
||||
* Unify academic and industrial model inference training scripts;
|
||||
|
||||
|
||||
|
||||
# Quick to get started
|
||||
|
||||
@ -51,19 +51,19 @@ Model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch
|
||||
```
|
||||
|
||||
* `model`(str): [Model Warehouse](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo)The model name in, or the model path in the local disk
|
||||
|
||||
|
||||
* `device`(str): `cuda:0`(Default gpu0), using GPU for inference, specified. If`cpu`Then the CPU is used for inference
|
||||
|
||||
|
||||
* `ncpu`(int): `4`(Default), set the number of threads used for CPU internal operation parallelism
|
||||
|
||||
|
||||
* `output_dir`(str): `None`(Default) If set, the output path of the output result
|
||||
|
||||
|
||||
* `batch_size`(int): `1`(Default), batch processing during decoding, number of samples
|
||||
|
||||
|
||||
* `hub`(str)：`ms`(Default) to download the model from modelscope. If`hf`To download the model from huggingface.
|
||||
|
||||
|
||||
* `**kwargs`(dict): All in`config.yaml`Parameters, which can be specified directly here, for example, the maximum cut length in the vad model.`max_single_segment_time=6000`(Milliseconds).
|
||||
|
||||
|
||||
|
||||
#### AutoModel reasoning
|
||||
|
||||
@ -72,13 +72,13 @@ Res = model.generate(input=[str], output_dir=[str])
|
||||
```
|
||||
|
||||
* * wav file path, for example: asr\_example.wav
|
||||
|
||||
|
||||
* pcm file path, for example: asr\_example.pcm, you need to specify the audio sampling rate fs (default is 16000)
|
||||
|
||||
|
||||
* Audio byte stream, for example: microphone byte data
|
||||
|
||||
|
||||
* wav.scp,kaldi-style wav list (`wav_id \t wav_path`), for example:
|
||||
|
||||
|
||||
|
||||
```plaintext
|
||||
Asr_example1./audios/asr_example1.wav
|
||||
@ -89,13 +89,13 @@ Asr_example2./audios/asr_example2.wav
|
||||
In this input
|
||||
|
||||
* Audio sampling points, for example:`audio, rate = soundfile.read("asr_example_zh.wav")`Is numpy.ndarray. batch input is supported. The type is list:`[audio_sample1, audio_sample2, ..., audio_sampleN]`
|
||||
|
||||
|
||||
* fbank input, support group batch. shape is \[batch, frames, dim\], type is torch.Tensor, for example
|
||||
|
||||
|
||||
* `output_dir`: None (default), if set, the output path of the output result
|
||||
|
||||
|
||||
* `**kwargs`(dict): Model-related inference parameters, e.g,`beam_size=10`,`decoding_ctc_weight=0.1`.
|
||||
|
||||
|
||||
|
||||
Detailed documentation link:[https://github.com/modelscope/FunASR/blob/main/examples/README\_zh.md](https://github.com/modelscope/FunASR/blob/main/examples/README_zh.md)
|
||||
|
||||
@ -128,7 +128,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
|
||||
@ -208,10 +208,10 @@ Path resolution: configuration.json (not required)
|
||||
"model": {"type" : "funasr"},
|
||||
"pipeline": {"type":"funasr-pipeline"},
|
||||
"model_name_in_hub": {
|
||||
"ms":"",
|
||||
"ms":"",
|
||||
"hf":""},
|
||||
"file_path_metas": {
|
||||
"init_param":"model.pt",
|
||||
"init_param":"model.pt",
|
||||
"config":"config.yaml",
|
||||
"tokenizer_conf": {"bpemodel": "chn_jpn_yue_eng_ko_spectok.bpe.model"},
|
||||
"frontend_conf":{"cmvn_file": "am.mvn"}}
|
||||
@ -274,7 +274,7 @@ class SenseVoiceSmall(nn.Module):
|
||||
def forward(
|
||||
self,
|
||||
**kwargs,
|
||||
):
|
||||
):
|
||||
|
||||
def inference(
|
||||
self,
|
||||
@ -320,9 +320,9 @@ from funasr.models.sense_voice.model import *
|
||||
## Principles of Registration
|
||||
|
||||
* Model: models are independent of each other. Each Model needs to create a new Model directory under funasr/models/. Do not use class inheritance method!!! Do not import from other model directories, and put everything you need into your own model directory!!! Do not modify the existing model code!!!
|
||||
|
||||
|
||||
* dataset,frontend,tokenizer, if you can reuse the existing one, reuse it directly, if you cannot reuse it, please register a new one, modify it again, and do not modify the original one!!!
|
||||
|
||||
|
||||
|
||||
# Independent warehouse
|
||||
|
||||
@ -337,7 +337,7 @@ from funasr import AutoModel
|
||||
model = AutoModel (
|
||||
model="iic/SenseVoiceSmall ",
|
||||
trust_remote_code=True
|
||||
remote_code = "./model.py",
|
||||
remote_code = "./model.py",
|
||||
)
|
||||
```
|
||||
|
||||
@ -360,4 +360,4 @@ res = m.inference(
|
||||
print(text)
|
||||
```
|
||||
|
||||
Trim reference:[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)
|
||||
Trim reference:[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)
|
||||
|
||||
@ -5,13 +5,13 @@
|
||||
funasr-1.x.x 版本的设计初衷是【**让模型集成更简单**】，核心feature为注册表与AutoModel：
|
||||
|
||||
* 注册表的引入，使得开发中可以用搭积木的方式接入模型，兼容多种task；
|
||||
|
||||
|
||||
* 新设计的AutoModel接口，统一modelscope、huggingface与funasr推理与训练接口，支持自由选择下载仓库；
|
||||
|
||||
|
||||
* 支持模型导出，demo级别服务部署，以及工业级别多并发服务部署；
|
||||
|
||||
|
||||
* 统一学术与工业模型推理训练脚本；
|
||||
|
||||
|
||||
|
||||
# 快速上手
|
||||
|
||||
@ -51,19 +51,19 @@ model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch
|
||||
```
|
||||
|
||||
* `model`(str): [模型仓库](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo) 中的模型名称，或本地磁盘中的模型路径
|
||||
|
||||
|
||||
* `device`(str): `cuda:0`（默认gpu0），使用 GPU 进行推理，指定。如果为`cpu`，则使用 CPU 进行推理
|
||||
|
||||
|
||||
* `ncpu`(int): `4` （默认），设置用于 CPU 内部操作并行性的线程数
|
||||
|
||||
|
||||
* `output_dir`(str): `None` （默认），如果设置，输出结果的输出路径
|
||||
|
||||
|
||||
* `batch_size`(int): `1` （默认），解码时的批处理，样本个数
|
||||
|
||||
|
||||
* `hub`(str)：`ms`（默认），从modelscope下载模型。如果为`hf`，从huggingface下载模型。
|
||||
|
||||
|
||||
* `**kwargs`(dict): 所有在`config.yaml`中参数，均可以直接在此处指定，例如，vad模型中最大切割长度 `max_single_segment_time=6000` （毫秒）。
|
||||
|
||||
|
||||
|
||||
#### AutoModel 推理
|
||||
|
||||
@ -72,13 +72,13 @@ res = model.generate(input=[str], output_dir=[str])
|
||||
```
|
||||
|
||||
* * wav文件路径, 例如: asr\_example.wav
|
||||
|
||||
|
||||
* pcm文件路径, 例如: asr\_example.pcm，此时需要指定音频采样率fs（默认为16000）
|
||||
|
||||
|
||||
* 音频字节数流，例如：麦克风的字节数数据
|
||||
|
||||
|
||||
* wav.scp，kaldi 样式的 wav 列表 (`wav_id \t wav_path`), 例如:
|
||||
|
||||
|
||||
|
||||
```plaintext
|
||||
asr_example1 ./audios/asr_example1.wav
|
||||
@ -89,13 +89,13 @@ asr_example2 ./audios/asr_example2.wav
|
||||
在这种输入
|
||||
|
||||
* 音频采样点，例如：`audio, rate = soundfile.read("asr_example_zh.wav")`, 数据类型为 numpy.ndarray。支持batch输入，类型为list： `[audio_sample1, audio_sample2, ..., audio_sampleN]`
|
||||
|
||||
|
||||
* fbank输入，支持组batch。shape为\[batch, frames, dim\]，类型为torch.Tensor，例如
|
||||
|
||||
|
||||
* `output_dir`: None （默认），如果设置，输出结果的输出路径
|
||||
|
||||
|
||||
* `**kwargs`(dict): 与模型相关的推理参数，例如，`beam_size=10`，`decoding_ctc_weight=0.1`。
|
||||
|
||||
|
||||
|
||||
详细文档链接：[https://github.com/modelscope/FunASR/blob/main/examples/README\_zh.md](https://github.com/modelscope/FunASR/blob/main/examples/README_zh.md)
|
||||
|
||||
@ -128,7 +128,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
|
||||
@ -208,10 +208,10 @@ scheduler_conf:
|
||||
"model": {"type" : "funasr"},
|
||||
"pipeline": {"type":"funasr-pipeline"},
|
||||
"model_name_in_hub": {
|
||||
"ms":"",
|
||||
"ms":"",
|
||||
"hf":""},
|
||||
"file_path_metas": {
|
||||
"init_param":"model.pt",
|
||||
"init_param":"model.pt",
|
||||
"config":"config.yaml",
|
||||
"tokenizer_conf": {"bpemodel": "chn_jpn_yue_eng_ko_spectok.bpe.model"},
|
||||
"frontend_conf":{"cmvn_file": "am.mvn"}}
|
||||
@ -274,7 +274,7 @@ class SenseVoiceSmall(nn.Module):
|
||||
def forward(
|
||||
self,
|
||||
**kwargs,
|
||||
):
|
||||
):
|
||||
|
||||
def inference(
|
||||
self,
|
||||
@ -320,9 +320,9 @@ from funasr.models.sense_voice.model import *
|
||||
## 注册原则
|
||||
|
||||
* Model：模型之间互相独立，每一个模型，都需要在funasr/models/下面新建一个模型目录，不要采用类的继承方法！！！不要从其他模型目录中import，所有需要用到的都单独放到自己的模型目录中！！！不要修改现有的模型代码！！！
|
||||
|
||||
|
||||
* dataset，frontend，tokenizer，如果能复用现有的，直接复用，如果不能复用，请注册一个新的，再修改，不要修改原来的！！！
|
||||
|
||||
|
||||
|
||||
# 独立仓库
|
||||
|
||||
@ -336,8 +336,8 @@ from funasr import AutoModel
|
||||
# trust_remote_code：`True` 表示 model 代码实现从 `remote_code` 处加载，`remote_code` 指定 `model` 具体代码的位置（例如，当前目录下的 `model.py`），支持绝对路径与相对路径，以及网络 url。
|
||||
model = AutoModel(
|
||||
model="iic/SenseVoiceSmall",
|
||||
trust_remote_code=True,
|
||||
remote_code="./model.py",
|
||||
trust_remote_code=True,
|
||||
remote_code="./model.py",
|
||||
)
|
||||
```
|
||||
|
||||
@ -360,4 +360,4 @@ res = m.inference(
|
||||
print(text)
|
||||
```
|
||||
|
||||
微调参考：[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)
|
||||
微调参考：[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)
|
||||
|
||||
@ -18,7 +18,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# frontend related
|
||||
|
||||
@ -18,7 +18,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
chunk_size:
|
||||
- 16
|
||||
|
||||
@ -30,7 +30,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# decoder
|
||||
@ -45,7 +45,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
predictor: CifPredictorV3
|
||||
predictor_conf:
|
||||
|
||||
@ -137,7 +137,7 @@ class ContextualParaformerDecoder(ParaformerSANMDecoder):
|
||||
concat_after: bool = False,
|
||||
att_layer_num: int = 6,
|
||||
kernel_size: int = 21,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
):
|
||||
super().__init__(
|
||||
vocab_size=vocab_size,
|
||||
@ -179,14 +179,14 @@ class ContextualParaformerDecoder(ParaformerSANMDecoder):
|
||||
|
||||
self.att_layer_num = att_layer_num
|
||||
self.num_blocks = num_blocks
|
||||
if sanm_shfit is None:
|
||||
sanm_shfit = (kernel_size - 1) // 2
|
||||
if sanm_shift is None:
|
||||
sanm_shift = (kernel_size - 1) // 2
|
||||
self.decoders = repeat(
|
||||
att_layer_num - 1,
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=sanm_shift
|
||||
),
|
||||
MultiHeadedAttentionCrossAtt(
|
||||
attention_heads, attention_dim, src_attention_dropout_rate
|
||||
@ -210,7 +210,7 @@ class ContextualParaformerDecoder(ParaformerSANMDecoder):
|
||||
self.last_decoder = ContextualDecoderLayer(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=sanm_shift
|
||||
),
|
||||
MultiHeadedAttentionCrossAtt(
|
||||
attention_heads, attention_dim, src_attention_dropout_rate
|
||||
@ -228,7 +228,7 @@ class ContextualParaformerDecoder(ParaformerSANMDecoder):
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=0
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=0
|
||||
),
|
||||
None,
|
||||
PositionwiseFeedForwardDecoderSANM(attention_dim, linear_units, dropout_rate),
|
||||
|
||||
@ -30,7 +30,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
|
||||
@ -46,7 +46,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
predictor: CifPredictorV2
|
||||
predictor_conf:
|
||||
@ -126,4 +126,4 @@ ctc_conf:
|
||||
ctc_type: builtin
|
||||
reduce: true
|
||||
ignore_nan_grad: true
|
||||
normalize: null
|
||||
normalize: null
|
||||
|
||||
@ -41,7 +41,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
padding_idx: 0
|
||||
|
||||
|
||||
@ -11,9 +11,9 @@ class MultiHeadedAttentionSANMwithMask(MultiHeadedAttentionSANM):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
q_h, k_h, v_h, v = self.forward_qkv(x)
|
||||
fsmn_memory = self.forward_fsmn(v, mask[0], mask_shfit_chunk)
|
||||
fsmn_memory = self.forward_fsmn(v, mask[0], mask_shift_chunk)
|
||||
q_h = q_h * self.d_k ** (-0.5)
|
||||
scores = torch.matmul(q_h, k_h.transpose(-2, -1))
|
||||
att_outs = self.forward_attention(v_h, scores, mask[1], mask_att_chunk_encoder)
|
||||
|
||||
@ -56,7 +56,7 @@ class EncoderLayerSANM(torch.nn.Module):
|
||||
self.stochastic_depth_rate = stochastic_depth_rate
|
||||
self.dropout_rate = dropout_rate
|
||||
|
||||
def forward(self, x, mask, cache=None, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, cache=None, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute encoded features.
|
||||
|
||||
Args:
|
||||
@ -93,7 +93,7 @@ class EncoderLayerSANM(torch.nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
),
|
||||
),
|
||||
@ -109,7 +109,7 @@ class EncoderLayerSANM(torch.nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -118,7 +118,7 @@ class EncoderLayerSANM(torch.nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -132,7 +132,7 @@ class EncoderLayerSANM(torch.nn.Module):
|
||||
if not self.normalize_before:
|
||||
x = self.norm2(x)
|
||||
|
||||
return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
return x, mask, cache, mask_shift_chunk, mask_att_chunk_encoder
|
||||
|
||||
def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
|
||||
"""Compute encoded features.
|
||||
@ -198,7 +198,7 @@ class SANMVadEncoder(torch.nn.Module):
|
||||
interctc_layer_idx: List[int] = [],
|
||||
interctc_use_conditioning: bool = False,
|
||||
kernel_size: int = 11,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
selfattention_layer_type: str = "sanm",
|
||||
):
|
||||
super().__init__()
|
||||
@ -277,7 +277,7 @@ class SANMVadEncoder(torch.nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
|
||||
encoder_selfattn_layer_args = (
|
||||
@ -286,7 +286,7 @@ class SANMVadEncoder(torch.nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
|
||||
self.encoders0 = repeat(
|
||||
|
||||
@ -41,10 +41,10 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 5
|
||||
sanm_shift: 5
|
||||
selfattention_layer_type: sanm
|
||||
padding_idx: 0
|
||||
|
||||
tokenizer: CharTokenizer
|
||||
tokenizer_conf:
|
||||
unk_symbol: <unk>
|
||||
unk_symbol: <unk>
|
||||
|
||||
@ -25,7 +25,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
predictor: CifPredictorV3
|
||||
@ -111,5 +111,5 @@ ctc_conf:
|
||||
ctc_type: builtin
|
||||
reduce: true
|
||||
ignore_nan_grad: true
|
||||
|
||||
|
||||
normalize: null
|
||||
|
||||
@ -248,7 +248,7 @@ class ParaformerSANMDecoder(BaseTransformerDecoder):
|
||||
concat_after: bool = False,
|
||||
att_layer_num: int = 6,
|
||||
kernel_size: int = 21,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
lora_list: List[str] = None,
|
||||
lora_rank: int = 8,
|
||||
lora_alpha: int = 16,
|
||||
@ -298,14 +298,14 @@ class ParaformerSANMDecoder(BaseTransformerDecoder):
|
||||
|
||||
self.att_layer_num = att_layer_num
|
||||
self.num_blocks = num_blocks
|
||||
if sanm_shfit is None:
|
||||
sanm_shfit = (kernel_size - 1) // 2
|
||||
if sanm_shift is None:
|
||||
sanm_shift = (kernel_size - 1) // 2
|
||||
self.decoders = repeat(
|
||||
att_layer_num,
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=sanm_shift
|
||||
),
|
||||
MultiHeadedAttentionCrossAtt(
|
||||
attention_heads,
|
||||
@ -330,7 +330,7 @@ class ParaformerSANMDecoder(BaseTransformerDecoder):
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=0
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=0
|
||||
),
|
||||
None,
|
||||
PositionwiseFeedForwardDecoderSANM(attention_dim, linear_units, dropout_rate),
|
||||
@ -785,20 +785,20 @@ class ParaformerSANMDecoderExport(torch.nn.Module):
|
||||
for _ in range(cache_num)
|
||||
]
|
||||
return (tgt, memory, pre_acoustic_embeds, cache)
|
||||
|
||||
|
||||
def is_optimizable(self):
|
||||
return True
|
||||
|
||||
|
||||
def get_input_names(self):
|
||||
cache_num = len(self.model.decoders) + len(self.model.decoders2)
|
||||
return ['tgt', 'memory', 'pre_acoustic_embeds'] \
|
||||
+ ['cache_%d' % i for i in range(cache_num)]
|
||||
|
||||
|
||||
def get_output_names(self):
|
||||
cache_num = len(self.model.decoders) + len(self.model.decoders2)
|
||||
return ['y'] \
|
||||
+ ['out_cache_%d' % i for i in range(cache_num)]
|
||||
|
||||
|
||||
def get_dynamic_axes(self):
|
||||
ret = {
|
||||
'tgt': {
|
||||
|
||||
@ -29,7 +29,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# decoder
|
||||
@ -44,7 +44,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
predictor: CifPredictorV2
|
||||
predictor_conf:
|
||||
|
||||
@ -198,10 +198,10 @@ class ParaformerStreaming(Paraformer):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor(
|
||||
encoder_out,
|
||||
ys_pad,
|
||||
@ -357,10 +357,10 @@ class ParaformerStreaming(Paraformer):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, pre_peak_index = self.predictor(
|
||||
encoder_out,
|
||||
None,
|
||||
|
||||
@ -29,7 +29,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
chunk_size:
|
||||
- 12
|
||||
@ -59,7 +59,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 5
|
||||
sanm_shift: 5
|
||||
|
||||
predictor: CifPredictorV2
|
||||
predictor_conf:
|
||||
|
||||
@ -154,7 +154,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
n_feat,
|
||||
dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit=0,
|
||||
sanm_shift=0,
|
||||
lora_list=None,
|
||||
lora_rank=8,
|
||||
lora_alpha=16,
|
||||
@ -199,17 +199,17 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
)
|
||||
# padding
|
||||
left_padding = (kernel_size - 1) // 2
|
||||
if sanm_shfit > 0:
|
||||
left_padding = left_padding + sanm_shfit
|
||||
if sanm_shift > 0:
|
||||
left_padding = left_padding + sanm_shift
|
||||
right_padding = kernel_size - 1 - left_padding
|
||||
self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
|
||||
|
||||
def forward_fsmn(self, inputs, mask, mask_shfit_chunk=None):
|
||||
def forward_fsmn(self, inputs, mask, mask_shift_chunk=None):
|
||||
b, t, d = inputs.size()
|
||||
if mask is not None:
|
||||
mask = torch.reshape(mask, (b, -1, 1))
|
||||
if mask_shfit_chunk is not None:
|
||||
mask = mask * mask_shfit_chunk
|
||||
if mask_shift_chunk is not None:
|
||||
mask = mask * mask_shift_chunk
|
||||
inputs = inputs * mask
|
||||
|
||||
x = inputs.transpose(1, 2)
|
||||
@ -289,7 +289,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
|
||||
return self.linear_out(x) # (batch, time1, d_model)
|
||||
|
||||
def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute scaled dot product attention.
|
||||
|
||||
Args:
|
||||
@ -304,7 +304,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
|
||||
"""
|
||||
q_h, k_h, v_h, v = self.forward_qkv(x)
|
||||
fsmn_memory = self.forward_fsmn(v, mask, mask_shfit_chunk)
|
||||
fsmn_memory = self.forward_fsmn(v, mask, mask_shift_chunk)
|
||||
q_h = q_h * self.d_k ** (-0.5)
|
||||
scores = torch.matmul(q_h, k_h.transpose(-2, -1))
|
||||
att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
|
||||
@ -478,7 +478,7 @@ class MultiHeadedAttentionSANMDecoder(nn.Module):
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, n_feat, dropout_rate, kernel_size, sanm_shfit=0):
|
||||
def __init__(self, n_feat, dropout_rate, kernel_size, sanm_shift=0):
|
||||
"""Construct an MultiHeadedAttention object."""
|
||||
super().__init__()
|
||||
|
||||
@ -490,13 +490,13 @@ class MultiHeadedAttentionSANMDecoder(nn.Module):
|
||||
# padding
|
||||
# padding
|
||||
left_padding = (kernel_size - 1) // 2
|
||||
if sanm_shfit > 0:
|
||||
left_padding = left_padding + sanm_shfit
|
||||
if sanm_shift > 0:
|
||||
left_padding = left_padding + sanm_shift
|
||||
right_padding = kernel_size - 1 - left_padding
|
||||
self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
|
||||
self.kernel_size = kernel_size
|
||||
|
||||
def forward(self, inputs, mask, cache=None, mask_shfit_chunk=None):
|
||||
def forward(self, inputs, mask, cache=None, mask_shift_chunk=None):
|
||||
"""
|
||||
:param x: (#batch, time1, size).
|
||||
:param mask: Mask tensor (#batch, 1, time)
|
||||
@ -509,9 +509,9 @@ class MultiHeadedAttentionSANMDecoder(nn.Module):
|
||||
if mask is not None:
|
||||
mask = torch.reshape(mask, (b, -1, 1))
|
||||
# logging.info("in fsmn, mask: {}, {}".format(mask.size(), mask[0:100:50, :, :]))
|
||||
if mask_shfit_chunk is not None:
|
||||
# logging.info("in fsmn, mask_fsmn: {}, {}".format(mask_shfit_chunk.size(), mask_shfit_chunk[0:100:50, :, :]))
|
||||
mask = mask * mask_shfit_chunk
|
||||
if mask_shift_chunk is not None:
|
||||
# logging.info("in fsmn, mask_fsmn: {}, {}".format(mask_shift_chunk.size(), mask_shift_chunk[0:100:50, :, :]))
|
||||
mask = mask * mask_shift_chunk
|
||||
# logging.info("in fsmn, mask_after_fsmn: {}, {}".format(mask.size(), mask[0:100:50, :, :]))
|
||||
# print("in fsmn, mask", mask.size())
|
||||
# print("in fsmn, inputs", inputs.size())
|
||||
|
||||
@ -226,7 +226,7 @@ class FsmnDecoder(BaseTransformerDecoder):
|
||||
concat_after: bool = False,
|
||||
att_layer_num: int = 6,
|
||||
kernel_size: int = 21,
|
||||
sanm_shfit: int = None,
|
||||
sanm_shift: int = None,
|
||||
concat_embeds: bool = False,
|
||||
attention_dim: int = None,
|
||||
tf2torch_tensor_name_prefix_torch: str = "decoder",
|
||||
@ -271,14 +271,14 @@ class FsmnDecoder(BaseTransformerDecoder):
|
||||
|
||||
self.att_layer_num = att_layer_num
|
||||
self.num_blocks = num_blocks
|
||||
if sanm_shfit is None:
|
||||
sanm_shfit = (kernel_size - 1) // 2
|
||||
if sanm_shift is None:
|
||||
sanm_shift = (kernel_size - 1) // 2
|
||||
self.decoders = repeat(
|
||||
att_layer_num,
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=sanm_shift
|
||||
),
|
||||
MultiHeadedAttentionCrossAtt(
|
||||
attention_heads,
|
||||
@ -303,7 +303,7 @@ class FsmnDecoder(BaseTransformerDecoder):
|
||||
attention_dim,
|
||||
self_attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit=sanm_shfit,
|
||||
sanm_shift=sanm_shift,
|
||||
),
|
||||
None,
|
||||
PositionwiseFeedForwardDecoderSANM(attention_dim, linear_units, dropout_rate),
|
||||
|
||||
@ -69,7 +69,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.stochastic_depth_rate = stochastic_depth_rate
|
||||
self.dropout_rate = dropout_rate
|
||||
|
||||
def forward(self, x, mask, cache=None, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, cache=None, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute encoded features.
|
||||
|
||||
Args:
|
||||
@ -106,7 +106,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
),
|
||||
),
|
||||
@ -122,7 +122,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -131,7 +131,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -145,7 +145,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
if not self.normalize_before:
|
||||
x = self.norm2(x)
|
||||
|
||||
return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
return x, mask, cache, mask_shift_chunk, mask_att_chunk_encoder
|
||||
|
||||
def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
|
||||
"""Compute encoded features.
|
||||
@ -212,7 +212,7 @@ class SANMEncoder(nn.Module):
|
||||
interctc_layer_idx: List[int] = [],
|
||||
interctc_use_conditioning: bool = False,
|
||||
kernel_size: int = 11,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
lora_list: List[str] = None,
|
||||
lora_rank: int = 8,
|
||||
lora_alpha: int = 16,
|
||||
@ -299,7 +299,7 @@ class SANMEncoder(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
lora_list,
|
||||
lora_rank,
|
||||
lora_alpha,
|
||||
@ -312,7 +312,7 @@ class SANMEncoder(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
lora_list,
|
||||
lora_rank,
|
||||
lora_alpha,
|
||||
|
||||
@ -26,7 +26,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# decoder
|
||||
@ -41,7 +41,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
|
||||
|
||||
|
||||
@ -21,7 +21,7 @@ class overlap_chunk:
|
||||
stride: tuple = (10,),
|
||||
pad_left: tuple = (0,),
|
||||
encoder_att_look_back_factor: tuple = (1,),
|
||||
shfit_fsmn: int = 0,
|
||||
shift_fsmn: int = 0,
|
||||
decoder_att_look_back_factor: tuple = (1,),
|
||||
):
|
||||
|
||||
@ -45,11 +45,11 @@ class overlap_chunk:
|
||||
encoder_att_look_back_factor,
|
||||
decoder_att_look_back_factor,
|
||||
)
|
||||
self.shfit_fsmn = shfit_fsmn
|
||||
self.shift_fsmn = shift_fsmn
|
||||
self.x_add_mask = None
|
||||
self.x_rm_mask = None
|
||||
self.x_len = None
|
||||
self.mask_shfit_chunk = None
|
||||
self.mask_shift_chunk = None
|
||||
self.mask_chunk_predictor = None
|
||||
self.mask_att_chunk_encoder = None
|
||||
self.mask_shift_att_chunk_decoder = None
|
||||
@ -88,7 +88,7 @@ class overlap_chunk:
|
||||
stride,
|
||||
pad_left,
|
||||
encoder_att_look_back_factor,
|
||||
chunk_size + self.shfit_fsmn,
|
||||
chunk_size + self.shift_fsmn,
|
||||
decoder_att_look_back_factor,
|
||||
)
|
||||
return (
|
||||
@ -118,13 +118,13 @@ class overlap_chunk:
|
||||
chunk_size, stride, pad_left, encoder_att_look_back_factor, chunk_size_pad_shift = (
|
||||
self.get_chunk_size(ind)
|
||||
)
|
||||
shfit_fsmn = self.shfit_fsmn
|
||||
shift_fsmn = self.shift_fsmn
|
||||
pad_right = chunk_size - stride - pad_left
|
||||
|
||||
chunk_num_batch = np.ceil(x_len / stride).astype(np.int32)
|
||||
x_len_chunk = (
|
||||
(chunk_num_batch - 1) * chunk_size_pad_shift
|
||||
+ shfit_fsmn
|
||||
+ shift_fsmn
|
||||
+ pad_left
|
||||
+ 0
|
||||
+ x_len
|
||||
@ -138,13 +138,13 @@ class overlap_chunk:
|
||||
max_len_for_x_mask_tmp = max(chunk_size, x_len_max + pad_left)
|
||||
x_add_mask = np.zeros([0, max_len_for_x_mask_tmp], dtype=dtype)
|
||||
x_rm_mask = np.zeros([max_len_for_x_mask_tmp, 0], dtype=dtype)
|
||||
mask_shfit_chunk = np.zeros([0, num_units], dtype=dtype)
|
||||
mask_shift_chunk = np.zeros([0, num_units], dtype=dtype)
|
||||
mask_chunk_predictor = np.zeros([0, num_units_predictor], dtype=dtype)
|
||||
mask_shift_att_chunk_decoder = np.zeros([0, 1], dtype=dtype)
|
||||
mask_att_chunk_encoder = np.zeros([0, chunk_num * chunk_size_pad_shift], dtype=dtype)
|
||||
for chunk_ids in range(chunk_num):
|
||||
# x_mask add
|
||||
fsmn_padding = np.zeros((shfit_fsmn, max_len_for_x_mask_tmp), dtype=dtype)
|
||||
fsmn_padding = np.zeros((shift_fsmn, max_len_for_x_mask_tmp), dtype=dtype)
|
||||
x_mask_cur = np.diag(np.ones(chunk_size, dtype=np.float32))
|
||||
x_mask_pad_left = np.zeros((chunk_size, chunk_ids * stride), dtype=dtype)
|
||||
x_mask_pad_right = np.zeros((chunk_size, max_len_for_x_mask_tmp), dtype=dtype)
|
||||
@ -154,7 +154,7 @@ class overlap_chunk:
|
||||
x_add_mask = np.concatenate([x_add_mask, x_add_mask_fsmn], axis=0)
|
||||
|
||||
# x_mask rm
|
||||
fsmn_padding = np.zeros((max_len_for_x_mask_tmp, shfit_fsmn), dtype=dtype)
|
||||
fsmn_padding = np.zeros((max_len_for_x_mask_tmp, shift_fsmn), dtype=dtype)
|
||||
padding_mask_left = np.zeros((max_len_for_x_mask_tmp, pad_left), dtype=dtype)
|
||||
padding_mask_right = np.zeros((max_len_for_x_mask_tmp, pad_right), dtype=dtype)
|
||||
x_mask_cur = np.diag(np.ones(stride, dtype=dtype))
|
||||
@ -170,13 +170,13 @@ class overlap_chunk:
|
||||
x_rm_mask = np.concatenate([x_rm_mask, x_rm_mask_cur_fsmn], axis=1)
|
||||
|
||||
# fsmn_padding_mask
|
||||
pad_shfit_mask = np.zeros([shfit_fsmn, num_units], dtype=dtype)
|
||||
pad_shift_mask = np.zeros([shift_fsmn, num_units], dtype=dtype)
|
||||
ones_1 = np.ones([chunk_size, num_units], dtype=dtype)
|
||||
mask_shfit_chunk_cur = np.concatenate([pad_shfit_mask, ones_1], axis=0)
|
||||
mask_shfit_chunk = np.concatenate([mask_shfit_chunk, mask_shfit_chunk_cur], axis=0)
|
||||
mask_shift_chunk_cur = np.concatenate([pad_shift_mask, ones_1], axis=0)
|
||||
mask_shift_chunk = np.concatenate([mask_shift_chunk, mask_shift_chunk_cur], axis=0)
|
||||
|
||||
# predictor mask
|
||||
zeros_1 = np.zeros([shfit_fsmn + pad_left, num_units_predictor], dtype=dtype)
|
||||
zeros_1 = np.zeros([shift_fsmn + pad_left, num_units_predictor], dtype=dtype)
|
||||
ones_2 = np.ones([stride, num_units_predictor], dtype=dtype)
|
||||
zeros_3 = np.zeros(
|
||||
[chunk_size - stride - pad_left, num_units_predictor], dtype=dtype
|
||||
@ -188,13 +188,13 @@ class overlap_chunk:
|
||||
)
|
||||
|
||||
# encoder att mask
|
||||
zeros_1_top = np.zeros([shfit_fsmn, chunk_num * chunk_size_pad_shift], dtype=dtype)
|
||||
zeros_1_top = np.zeros([shift_fsmn, chunk_num * chunk_size_pad_shift], dtype=dtype)
|
||||
|
||||
zeros_2_num = max(chunk_ids - encoder_att_look_back_factor, 0)
|
||||
zeros_2 = np.zeros([chunk_size, zeros_2_num * chunk_size_pad_shift], dtype=dtype)
|
||||
|
||||
encoder_att_look_back_num = max(chunk_ids - zeros_2_num, 0)
|
||||
zeros_2_left = np.zeros([chunk_size, shfit_fsmn], dtype=dtype)
|
||||
zeros_2_left = np.zeros([chunk_size, shift_fsmn], dtype=dtype)
|
||||
ones_2_mid = np.ones([stride, stride], dtype=dtype)
|
||||
zeros_2_bottom = np.zeros([chunk_size - stride, stride], dtype=dtype)
|
||||
zeros_2_right = np.zeros([chunk_size, chunk_size - stride], dtype=dtype)
|
||||
@ -202,7 +202,7 @@ class overlap_chunk:
|
||||
ones_2 = np.concatenate([zeros_2_left, ones_2, zeros_2_right], axis=1)
|
||||
ones_2 = np.tile(ones_2, [1, encoder_att_look_back_num])
|
||||
|
||||
zeros_3_left = np.zeros([chunk_size, shfit_fsmn], dtype=dtype)
|
||||
zeros_3_left = np.zeros([chunk_size, shift_fsmn], dtype=dtype)
|
||||
ones_3_right = np.ones([chunk_size, chunk_size], dtype=dtype)
|
||||
ones_3 = np.concatenate([zeros_3_left, ones_3_right], axis=1)
|
||||
|
||||
@ -218,7 +218,7 @@ class overlap_chunk:
|
||||
)
|
||||
|
||||
# decoder fsmn_shift_att_mask
|
||||
zeros_1 = np.zeros([shfit_fsmn, 1])
|
||||
zeros_1 = np.zeros([shift_fsmn, 1])
|
||||
ones_1 = np.ones([chunk_size, 1])
|
||||
mask_shift_att_chunk_decoder_cur = np.concatenate([zeros_1, ones_1], axis=0)
|
||||
mask_shift_att_chunk_decoder = np.concatenate(
|
||||
@ -229,7 +229,7 @@ class overlap_chunk:
|
||||
self.x_len_chunk = x_len_chunk
|
||||
self.x_rm_mask = x_rm_mask[:x_len_max, :x_len_chunk_max]
|
||||
self.x_len = x_len
|
||||
self.mask_shfit_chunk = mask_shfit_chunk[:x_len_chunk_max, :]
|
||||
self.mask_shift_chunk = mask_shift_chunk[:x_len_chunk_max, :]
|
||||
self.mask_chunk_predictor = mask_chunk_predictor[:x_len_chunk_max, :]
|
||||
self.mask_att_chunk_encoder = mask_att_chunk_encoder[:x_len_chunk_max, :x_len_chunk_max]
|
||||
self.mask_shift_att_chunk_decoder = mask_shift_att_chunk_decoder[:x_len_chunk_max, :]
|
||||
@ -238,7 +238,7 @@ class overlap_chunk:
|
||||
self.x_len_chunk,
|
||||
self.x_rm_mask,
|
||||
self.x_len,
|
||||
self.mask_shfit_chunk,
|
||||
self.mask_shift_chunk,
|
||||
self.mask_chunk_predictor,
|
||||
self.mask_att_chunk_encoder,
|
||||
self.mask_shift_att_chunk_decoder,
|
||||
@ -309,7 +309,7 @@ class overlap_chunk:
|
||||
x = torch.from_numpy(x).type(dtype).to(device)
|
||||
return x
|
||||
|
||||
def get_mask_shfit_chunk(
|
||||
def get_mask_shift_chunk(
|
||||
self, chunk_outs=None, device="cpu", batch_size=1, num_units=1, idx=4, dtype=torch.float32
|
||||
):
|
||||
with torch.no_grad():
|
||||
|
||||
@ -226,7 +226,7 @@ class FsmnDecoderSCAMAOpt(BaseTransformerDecoder):
|
||||
concat_after: bool = False,
|
||||
att_layer_num: int = 6,
|
||||
kernel_size: int = 21,
|
||||
sanm_shfit: int = None,
|
||||
sanm_shift: int = None,
|
||||
concat_embeds: bool = False,
|
||||
attention_dim: int = None,
|
||||
tf2torch_tensor_name_prefix_torch: str = "decoder",
|
||||
@ -271,14 +271,14 @@ class FsmnDecoderSCAMAOpt(BaseTransformerDecoder):
|
||||
|
||||
self.att_layer_num = att_layer_num
|
||||
self.num_blocks = num_blocks
|
||||
if sanm_shfit is None:
|
||||
sanm_shfit = (kernel_size - 1) // 2
|
||||
if sanm_shift is None:
|
||||
sanm_shift = (kernel_size - 1) // 2
|
||||
self.decoders = repeat(
|
||||
att_layer_num,
|
||||
lambda lnum: DecoderLayerSANM(
|
||||
attention_dim,
|
||||
MultiHeadedAttentionSANMDecoder(
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit
|
||||
attention_dim, self_attention_dropout_rate, kernel_size, sanm_shift=sanm_shift
|
||||
),
|
||||
MultiHeadedAttentionCrossAtt(
|
||||
attention_heads,
|
||||
@ -303,7 +303,7 @@ class FsmnDecoderSCAMAOpt(BaseTransformerDecoder):
|
||||
attention_dim,
|
||||
self_attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit=sanm_shfit,
|
||||
sanm_shift=sanm_shift,
|
||||
),
|
||||
None,
|
||||
PositionwiseFeedForwardDecoderSANM(attention_dim, linear_units, dropout_rate),
|
||||
|
||||
@ -69,7 +69,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.stochastic_depth_rate = stochastic_depth_rate
|
||||
self.dropout_rate = dropout_rate
|
||||
|
||||
def forward(self, x, mask, cache=None, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, cache=None, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute encoded features.
|
||||
|
||||
Args:
|
||||
@ -106,7 +106,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
),
|
||||
),
|
||||
@ -122,7 +122,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -131,7 +131,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -145,7 +145,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
if not self.normalize_before:
|
||||
x = self.norm2(x)
|
||||
|
||||
return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
return x, mask, cache, mask_shift_chunk, mask_att_chunk_encoder
|
||||
|
||||
def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
|
||||
"""Compute encoded features.
|
||||
@ -212,7 +212,7 @@ class SANMEncoderChunkOpt(nn.Module):
|
||||
interctc_layer_idx: List[int] = [],
|
||||
interctc_use_conditioning: bool = False,
|
||||
kernel_size: int = 11,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
selfattention_layer_type: str = "sanm",
|
||||
chunk_size: Union[int, Sequence[int]] = (16,),
|
||||
stride: Union[int, Sequence[int]] = (10,),
|
||||
@ -299,7 +299,7 @@ class SANMEncoderChunkOpt(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
|
||||
encoder_selfattn_layer_args = (
|
||||
@ -308,7 +308,7 @@ class SANMEncoderChunkOpt(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
self.encoders0 = repeat(
|
||||
1,
|
||||
@ -343,12 +343,12 @@ class SANMEncoderChunkOpt(nn.Module):
|
||||
assert 0 < min(interctc_layer_idx) and max(interctc_layer_idx) < num_blocks
|
||||
self.interctc_use_conditioning = interctc_use_conditioning
|
||||
self.conditioning_layer = None
|
||||
shfit_fsmn = (kernel_size - 1) // 2
|
||||
shift_fsmn = (kernel_size - 1) // 2
|
||||
self.overlap_chunk_cls = overlap_chunk(
|
||||
chunk_size=chunk_size,
|
||||
stride=stride,
|
||||
pad_left=pad_left,
|
||||
shfit_fsmn=shfit_fsmn,
|
||||
shift_fsmn=shift_fsmn,
|
||||
encoder_att_look_back_factor=encoder_att_look_back_factor,
|
||||
decoder_att_look_back_factor=decoder_att_look_back_factor,
|
||||
)
|
||||
@ -397,31 +397,31 @@ class SANMEncoderChunkOpt(nn.Module):
|
||||
else:
|
||||
xs_pad = self.embed(xs_pad)
|
||||
|
||||
mask_shfit_chunk, mask_att_chunk_encoder = None, None
|
||||
mask_shift_chunk, mask_att_chunk_encoder = None, None
|
||||
if self.overlap_chunk_cls is not None:
|
||||
ilens = masks.squeeze(1).sum(1)
|
||||
chunk_outs = self.overlap_chunk_cls.gen_chunk_mask(ilens, ind)
|
||||
xs_pad, ilens = self.overlap_chunk_cls.split_chunk(xs_pad, ilens, chunk_outs=chunk_outs)
|
||||
masks = (~make_pad_mask(ilens)[:, None, :]).to(xs_pad.device)
|
||||
mask_shfit_chunk = self.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
chunk_outs, xs_pad.device, xs_pad.size(0), dtype=xs_pad.dtype
|
||||
)
|
||||
mask_att_chunk_encoder = self.overlap_chunk_cls.get_mask_att_chunk_encoder(
|
||||
chunk_outs, xs_pad.device, xs_pad.size(0), dtype=xs_pad.dtype
|
||||
)
|
||||
|
||||
encoder_outs = self.encoders0(xs_pad, masks, None, mask_shfit_chunk, mask_att_chunk_encoder)
|
||||
encoder_outs = self.encoders0(xs_pad, masks, None, mask_shift_chunk, mask_att_chunk_encoder)
|
||||
xs_pad, masks = encoder_outs[0], encoder_outs[1]
|
||||
intermediate_outs = []
|
||||
if len(self.interctc_layer_idx) == 0:
|
||||
encoder_outs = self.encoders(
|
||||
xs_pad, masks, None, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
xs_pad, masks, None, mask_shift_chunk, mask_att_chunk_encoder
|
||||
)
|
||||
xs_pad, masks = encoder_outs[0], encoder_outs[1]
|
||||
else:
|
||||
for layer_idx, encoder_layer in enumerate(self.encoders):
|
||||
encoder_outs = encoder_layer(
|
||||
xs_pad, masks, None, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
xs_pad, masks, None, mask_shift_chunk, mask_att_chunk_encoder
|
||||
)
|
||||
xs_pad, masks = encoder_outs[0], encoder_outs[1]
|
||||
if layer_idx + 1 in self.interctc_layer_idx:
|
||||
|
||||
@ -321,10 +321,10 @@ class SCAMA(nn.Module):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
@ -415,10 +415,10 @@ class SCAMA(nn.Module):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
|
||||
@ -26,7 +26,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# decoder
|
||||
@ -41,7 +41,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
predictor: CifPredictorV2
|
||||
predictor_conf:
|
||||
|
||||
@ -36,7 +36,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
# decoder
|
||||
@ -51,7 +51,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
|
||||
# seaco decoder
|
||||
seaco_decoder: ParaformerSANMDecoder
|
||||
@ -64,7 +64,7 @@ seaco_decoder_conf:
|
||||
self_attention_dropout_rate: 0.1
|
||||
src_attention_dropout_rate: 0.1
|
||||
kernel_size: 21
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
use_output_layer: false
|
||||
wo_input_layer: true
|
||||
|
||||
|
||||
@ -95,7 +95,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
n_feat,
|
||||
dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit=0,
|
||||
sanm_shift=0,
|
||||
lora_list=None,
|
||||
lora_rank=8,
|
||||
lora_alpha=16,
|
||||
@ -121,17 +121,17 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
)
|
||||
# padding
|
||||
left_padding = (kernel_size - 1) // 2
|
||||
if sanm_shfit > 0:
|
||||
left_padding = left_padding + sanm_shfit
|
||||
if sanm_shift > 0:
|
||||
left_padding = left_padding + sanm_shift
|
||||
right_padding = kernel_size - 1 - left_padding
|
||||
self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
|
||||
|
||||
def forward_fsmn(self, inputs, mask, mask_shfit_chunk=None):
|
||||
def forward_fsmn(self, inputs, mask, mask_shift_chunk=None):
|
||||
b, t, d = inputs.size()
|
||||
if mask is not None:
|
||||
mask = torch.reshape(mask, (b, -1, 1))
|
||||
if mask_shfit_chunk is not None:
|
||||
mask = mask * mask_shfit_chunk
|
||||
if mask_shift_chunk is not None:
|
||||
mask = mask * mask_shift_chunk
|
||||
inputs = inputs * mask
|
||||
|
||||
x = inputs.transpose(1, 2)
|
||||
@ -211,7 +211,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
|
||||
return self.linear_out(x) # (batch, time1, d_model)
|
||||
|
||||
def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute scaled dot product attention.
|
||||
|
||||
Args:
|
||||
@ -226,7 +226,7 @@ class MultiHeadedAttentionSANM(nn.Module):
|
||||
|
||||
"""
|
||||
q_h, k_h, v_h, v = self.forward_qkv(x)
|
||||
fsmn_memory = self.forward_fsmn(v, mask, mask_shfit_chunk)
|
||||
fsmn_memory = self.forward_fsmn(v, mask, mask_shift_chunk)
|
||||
q_h = q_h * self.d_k ** (-0.5)
|
||||
scores = torch.matmul(q_h, k_h.transpose(-2, -1))
|
||||
att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
|
||||
@ -326,7 +326,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.stochastic_depth_rate = stochastic_depth_rate
|
||||
self.dropout_rate = dropout_rate
|
||||
|
||||
def forward(self, x, mask, cache=None, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
|
||||
def forward(self, x, mask, cache=None, mask_shift_chunk=None, mask_att_chunk_encoder=None):
|
||||
"""Compute encoded features.
|
||||
|
||||
Args:
|
||||
@ -363,7 +363,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
),
|
||||
),
|
||||
@ -379,7 +379,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -388,7 +388,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
self.self_attn(
|
||||
x,
|
||||
mask,
|
||||
mask_shfit_chunk=mask_shfit_chunk,
|
||||
mask_shift_chunk=mask_shift_chunk,
|
||||
mask_att_chunk_encoder=mask_att_chunk_encoder,
|
||||
)
|
||||
)
|
||||
@ -402,7 +402,7 @@ class EncoderLayerSANM(nn.Module):
|
||||
if not self.normalize_before:
|
||||
x = self.norm2(x)
|
||||
|
||||
return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder
|
||||
return x, mask, cache, mask_shift_chunk, mask_att_chunk_encoder
|
||||
|
||||
def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
|
||||
"""Compute encoded features.
|
||||
@ -469,7 +469,7 @@ class SenseVoiceEncoderSmall(nn.Module):
|
||||
positionwise_conv_kernel_size: int = 1,
|
||||
padding_idx: int = -1,
|
||||
kernel_size: int = 11,
|
||||
sanm_shfit: int = 0,
|
||||
sanm_shift: int = 0,
|
||||
selfattention_layer_type: str = "sanm",
|
||||
**kwargs,
|
||||
):
|
||||
@ -494,7 +494,7 @@ class SenseVoiceEncoderSmall(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
encoder_selfattn_layer_args = (
|
||||
attention_heads,
|
||||
@ -502,7 +502,7 @@ class SenseVoiceEncoderSmall(nn.Module):
|
||||
output_size,
|
||||
attention_dropout_rate,
|
||||
kernel_size,
|
||||
sanm_shfit,
|
||||
sanm_shift,
|
||||
)
|
||||
|
||||
self.encoders0 = nn.ModuleList(
|
||||
|
||||
@ -36,12 +36,12 @@ class FsmnBlock(torch.nn.Module):
|
||||
right_padding = kernel_size - 1 - left_padding
|
||||
self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
|
||||
|
||||
def forward(self, inputs, mask, mask_shfit_chunk=None):
|
||||
def forward(self, inputs, mask, mask_shift_chunk=None):
|
||||
b, t, d = inputs.size()
|
||||
if mask is not None:
|
||||
mask = torch.reshape(mask, (b, -1, 1))
|
||||
if mask_shfit_chunk is not None:
|
||||
mask = mask * mask_shfit_chunk
|
||||
if mask_shift_chunk is not None:
|
||||
mask = mask * mask_shift_chunk
|
||||
|
||||
inputs = inputs * mask
|
||||
x = inputs.transpose(1, 2)
|
||||
|
||||
@ -521,10 +521,10 @@ class UniASR(torch.nn.Module):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
@ -622,10 +622,10 @@ class UniASR(torch.nn.Module):
|
||||
mask_chunk_predictor = self.encoder2.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder2.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder2.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor2(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
@ -724,10 +724,10 @@ class UniASR(torch.nn.Module):
|
||||
mask_chunk_predictor = self.encoder.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
@ -806,10 +806,10 @@ class UniASR(torch.nn.Module):
|
||||
mask_chunk_predictor = self.encoder2.overlap_chunk_cls.get_mask_chunk_predictor(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
mask_shfit_chunk = self.encoder2.overlap_chunk_cls.get_mask_shfit_chunk(
|
||||
mask_shift_chunk = self.encoder2.overlap_chunk_cls.get_mask_shift_chunk(
|
||||
None, device=encoder_out.device, batch_size=encoder_out.size(0)
|
||||
)
|
||||
encoder_out = encoder_out * mask_shfit_chunk
|
||||
encoder_out = encoder_out * mask_shift_chunk
|
||||
pre_acoustic_embeds, pre_token_length, pre_alphas, _ = self.predictor2(
|
||||
encoder_out,
|
||||
ys_out_pad,
|
||||
|
||||
@ -33,7 +33,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
chunk_size:
|
||||
- 20
|
||||
@ -89,7 +89,7 @@ encoder2_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 21
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
chunk_size:
|
||||
- 45
|
||||
|
||||
@ -19,7 +19,7 @@ namespace AliParaformerAsr.Model
|
||||
private float _src_attention_dropout_rate = 0.1F;
|
||||
private int _att_layer_num = 16;
|
||||
private int _kernel_size = 11;
|
||||
private int _sanm_shfit = 0;
|
||||
private int _sanm_shift = 0;
|
||||
|
||||
public int attention_heads { get => _attention_heads; set => _attention_heads = value; }
|
||||
public int linear_units { get => _linear_units; set => _linear_units = value; }
|
||||
@ -30,7 +30,7 @@ namespace AliParaformerAsr.Model
|
||||
public float src_attention_dropout_rate { get => _src_attention_dropout_rate; set => _src_attention_dropout_rate = value; }
|
||||
public int att_layer_num { get => _att_layer_num; set => _att_layer_num = value; }
|
||||
public int kernel_size { get => _kernel_size; set => _kernel_size = value; }
|
||||
public int sanm_shfit { get => _sanm_shfit; set => _sanm_shfit = value; }
|
||||
|
||||
public int sanm_shift { get => _sanm_shift; set => _sanm_shift = value; }
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
@ -21,7 +21,7 @@ namespace AliParaformerAsr.Model
|
||||
private string _pos_enc_class = "SinusoidalPositionEncoder";
|
||||
private bool _normalize_before = true;
|
||||
private int _kernel_size = 11;
|
||||
private int _sanm_shfit = 0;
|
||||
private int _sanm_shift = 0;
|
||||
private string _selfattention_layer_type = "sanm";
|
||||
|
||||
public int output_size { get => _output_size; set => _output_size = value; }
|
||||
@ -35,7 +35,7 @@ namespace AliParaformerAsr.Model
|
||||
public string pos_enc_class { get => _pos_enc_class; set => _pos_enc_class = value; }
|
||||
public bool normalize_before { get => _normalize_before; set => _normalize_before = value; }
|
||||
public int kernel_size { get => _kernel_size; set => _kernel_size = value; }
|
||||
public int sanm_shfit { get => _sanm_shfit; set => _sanm_shfit = value; }
|
||||
public int sanm_shift { get => _sanm_shift; set => _sanm_shift = value; }
|
||||
public string selfattention_layer_type { get => _selfattention_layer_type; set => _selfattention_layer_type = value; }
|
||||
}
|
||||
}
|
||||
|
||||
@ -8593,7 +8593,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
chunk_size:
|
||||
- 12
|
||||
@ -8623,7 +8623,7 @@ decoder_conf:
|
||||
src_attention_dropout_rate: 0.1
|
||||
att_layer_num: 16
|
||||
kernel_size: 11
|
||||
sanm_shfit: 5
|
||||
sanm_shift: 5
|
||||
predictor: cif_predictor_v2
|
||||
predictor_conf:
|
||||
idim: 512
|
||||
|
||||
@ -12,7 +12,7 @@ encoder_conf:
|
||||
pos_enc_class: SinusoidalPositionEncoder
|
||||
normalize_before: true
|
||||
kernel_size: 11
|
||||
sanm_shfit: 0
|
||||
sanm_shift: 0
|
||||
selfattention_layer_type: sanm
|
||||
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user