File size: 5,096 Bytes
d3065b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
# ############################################################################
# Model: E2E ASR with Transformer
# Encoder: Conformer Encoder (small)
# Decoder: Transformer Decoder + (CTC/ATT joint) beamsearch + TransformerLM
# Tokens: unigram
# losses: CTC + KLdiv (Label Smoothing loss)
# Training: KsponSpeech 965.2h
# Based on the works of: Jianyuan Zhong, Titouan Parcollet 2021
# Authors: Dong Won Kim, Dongwoo Kim 2021, 2024
# ############################################################################
# Seed needs to be set at top of yaml, before objects with parameters are made
# ############################################################################

# Feature parameters
sample_rate: 16000
n_fft: 512
n_mels: 80

####################### Model parameters ###########################
# Transformer
d_model: 144
nhead: 4
num_encoder_layers: 12
num_decoder_layers: 4
d_ffn: 1024
transformer_dropout: 0.1
activation: !name:torch.nn.GELU
output_neurons: 5000

# Outputs
blank_index: 0
label_smoothing: 0.1
pad_index: 0
bos_index: 1
eos_index: 2

# Decoding parameters
min_decode_ratio: 0.0
max_decode_ratio: 1.0
test_beam_size: 66
lm_weight: 0.60
ctc_weight_decode: 0.40

############################## models ################################

CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd
    input_shape: (8, 10, 80)
    num_blocks: 2
    num_layers_per_block: 1
    out_channels: (64, 32)
    kernel_sizes: (3, 3)
    strides: (2, 2)
    residuals: (False, False)

Transformer: !new:speechbrain.lobes.models.transformer.TransformerASR.TransformerASR # yamllint disable-line rule:line-length
    input_size: 640
    tgt_vocab: !ref <output_neurons>
    d_model: !ref <d_model>
    nhead: !ref <nhead>
    num_encoder_layers: !ref <num_encoder_layers>
    num_decoder_layers: !ref <num_decoder_layers>
    d_ffn: !ref <d_ffn>
    activation: !ref <activation>
    encoder_module: conformer
    attention_type: RelPosMHAXL
    normalize_before: True
    causal: False

ctc_lin: !new:speechbrain.nnet.linear.Linear
    input_size: !ref <d_model>
    n_neurons: !ref <output_neurons>

seq_lin: !new:speechbrain.nnet.linear.Linear
    input_size: !ref <d_model>
    n_neurons: !ref <output_neurons>

transformerlm_scorer: !new:speechbrain.decoders.scorer.TransformerLMScorer
   language_model: !ref <lm_model>
   temperature: 1.15
   
ctc_scorer: !new:speechbrain.decoders.scorer.CTCScorer
    eos_index: !ref <eos_index>
    blank_index: !ref <blank_index>
    ctc_fc: !ref <ctc_lin>
    
scorer: !new:speechbrain.decoders.scorer.ScorerBuilder
    full_scorers: [!ref <transformerlm_scorer>, !ref <ctc_scorer>]
    weights:
        transformerlm: !ref <lm_weight>
        ctc: !ref <ctc_weight_decode>

        
decoder: !new:speechbrain.decoders.S2STransformerBeamSearcher
    modules: [!ref <Transformer>, !ref <seq_lin>]
    bos_index: !ref <bos_index>
    eos_index: !ref <eos_index>
    min_decode_ratio: !ref <min_decode_ratio>
    max_decode_ratio: !ref <max_decode_ratio>
    beam_size: !ref <test_beam_size>
    temperature: 1.15
    using_eos_threshold: False
    length_normalization: True
    scorer: !ref <scorer>

log_softmax: !new:torch.nn.LogSoftmax
    dim: -1

normalizer: !new:speechbrain.processing.features.InputNormalization
    norm_type: global

compute_features: !new:speechbrain.lobes.features.Fbank
    sample_rate: !ref <sample_rate>
    n_fft: !ref <n_fft>
    n_mels: !ref <n_mels>

# This is the Transformer LM that is used according to the Huggingface repository
# Visit the HuggingFace model corresponding to the pretrained_lm_tokenizer_path
# For more details about the model!
# NB: It has to match the pre-trained TransformerLM!!
lm_model: !new:speechbrain.lobes.models.transformer.TransformerLM.TransformerLM
    vocab: 5000
    d_model: 768
    nhead: 12
    num_encoder_layers: 12
    num_decoder_layers: 0
    d_ffn: 3072
    dropout: 0.0
    activation: !name:torch.nn.GELU
    normalize_before: False

tokenizer: !new:sentencepiece.SentencePieceProcessor

Tencoder: !new:speechbrain.lobes.models.transformer.TransformerASR.EncoderWrapper
    transformer: !ref <Transformer>

encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
    input_shape: [null, null, !ref <n_mels>]
    compute_features: !ref <compute_features>
    normalize: !ref <normalizer>
    cnn: !ref <CNN>
    transformer_encoder: !ref <Tencoder>

# Models
asr_model: !new:torch.nn.ModuleList
    - [!ref <CNN>, !ref <Transformer>, !ref <seq_lin>, !ref <ctc_lin>]

modules:
   compute_features: !ref <compute_features>
   normalizer: !ref <normalizer>
   pre_transformer: !ref <CNN>
   transformer: !ref <Transformer>
   asr_model: !ref <asr_model>
   lm_model: !ref <lm_model>
   encoder: !ref <encoder>
   decoder: !ref <decoder>

# The pretrainer allows a mapping between pretrained files and instances that
# are declared in the yaml.
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
   loadables:
      normalizer: !ref <normalizer>
      asr: !ref <asr_model>
      lm: !ref <lm_model>
      tokenizer: !ref <tokenizer>