speechbrainteam
commited on
Commit
•
b8f6b8f
1
Parent(s):
3c12864
Delete hyperparams.yaml
Browse files- hyperparams.yaml +0 -118
hyperparams.yaml
DELETED
@@ -1,118 +0,0 @@
|
|
1 |
-
# ################################
|
2 |
-
# Model: wav2vec2 + DNN + CTC/Attention
|
3 |
-
# Augmentation: SpecAugment
|
4 |
-
# Authors: Titouan Parcollet 2021
|
5 |
-
# ################################
|
6 |
-
|
7 |
-
sample_rate: 16000
|
8 |
-
wav2vec2_hub: facebook/wav2vec2-large-xlsr-53
|
9 |
-
|
10 |
-
# BPE parameters
|
11 |
-
token_type: unigram # ["unigram", "bpe", "char"]
|
12 |
-
character_coverage: 1.0
|
13 |
-
|
14 |
-
# Model parameters
|
15 |
-
activation: !name:torch.nn.LeakyReLU
|
16 |
-
dnn_layers: 2
|
17 |
-
dnn_neurons: 1024
|
18 |
-
emb_size: 128
|
19 |
-
dec_neurons: 1024
|
20 |
-
|
21 |
-
# Outputs
|
22 |
-
output_neurons: 1000 # BPE size, index(blank/eos/bos) = 0
|
23 |
-
|
24 |
-
# Decoding parameters
|
25 |
-
# Be sure that the bos and eos index match with the BPEs ones
|
26 |
-
blank_index: 0
|
27 |
-
bos_index: 1
|
28 |
-
eos_index: 2
|
29 |
-
min_decode_ratio: 0.0
|
30 |
-
max_decode_ratio: 1.0
|
31 |
-
beam_size: 10
|
32 |
-
eos_threshold: 1.5
|
33 |
-
using_max_attn_shift: True
|
34 |
-
max_attn_shift: 140
|
35 |
-
ctc_weight_decode: 0.0
|
36 |
-
temperature: 1.50
|
37 |
-
|
38 |
-
enc: !new:speechbrain.lobes.models.VanillaNN.VanillaNN
|
39 |
-
input_shape: [null, null, 1024]
|
40 |
-
activation: !ref <activation>
|
41 |
-
dnn_blocks: !ref <dnn_layers>
|
42 |
-
dnn_neurons: !ref <dnn_neurons>
|
43 |
-
|
44 |
-
wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
|
45 |
-
source: !ref <wav2vec2_hub>
|
46 |
-
output_norm: True
|
47 |
-
freeze: True
|
48 |
-
save_path: model_checkpoints
|
49 |
-
|
50 |
-
emb: !new:speechbrain.nnet.embedding.Embedding
|
51 |
-
num_embeddings: !ref <output_neurons>
|
52 |
-
embedding_dim: !ref <emb_size>
|
53 |
-
|
54 |
-
dec: !new:speechbrain.nnet.RNN.AttentionalRNNDecoder
|
55 |
-
enc_dim: !ref <dnn_neurons>
|
56 |
-
input_size: !ref <emb_size>
|
57 |
-
rnn_type: gru
|
58 |
-
attn_type: location
|
59 |
-
hidden_size: 1024
|
60 |
-
attn_dim: 1024
|
61 |
-
num_layers: 1
|
62 |
-
scaling: 1.0
|
63 |
-
channels: 10
|
64 |
-
kernel_size: 100
|
65 |
-
re_init: True
|
66 |
-
dropout: 0.0
|
67 |
-
|
68 |
-
ctc_lin: !new:speechbrain.nnet.linear.Linear
|
69 |
-
input_size: !ref <dnn_neurons>
|
70 |
-
n_neurons: !ref <output_neurons>
|
71 |
-
|
72 |
-
seq_lin: !new:speechbrain.nnet.linear.Linear
|
73 |
-
input_size: !ref <dec_neurons>
|
74 |
-
n_neurons: !ref <output_neurons>
|
75 |
-
|
76 |
-
log_softmax: !new:speechbrain.nnet.activations.Softmax
|
77 |
-
apply_log: True
|
78 |
-
|
79 |
-
ctc_cost: !name:speechbrain.nnet.losses.ctc_loss
|
80 |
-
blank_index: !ref <blank_index>
|
81 |
-
|
82 |
-
seq_cost: !name:speechbrain.nnet.losses.nll_loss
|
83 |
-
label_smoothing: 0.1
|
84 |
-
|
85 |
-
asr_model: !new:torch.nn.ModuleList
|
86 |
-
- [!ref <enc>, !ref <emb>, !ref <dec>, !ref <ctc_lin>, !ref <seq_lin>]
|
87 |
-
|
88 |
-
tokenizer: !new:sentencepiece.SentencePieceProcessor
|
89 |
-
|
90 |
-
encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
|
91 |
-
wav2vec2: !ref <wav2vec2>
|
92 |
-
enc: !ref <enc>
|
93 |
-
|
94 |
-
decoder: !new:speechbrain.decoders.S2SRNNBeamSearcher
|
95 |
-
embedding: !ref <emb>
|
96 |
-
decoder: !ref <dec>
|
97 |
-
linear: !ref <seq_lin>
|
98 |
-
ctc_linear: !ref <ctc_lin>
|
99 |
-
bos_index: !ref <bos_index>
|
100 |
-
eos_index: !ref <eos_index>
|
101 |
-
blank_index: !ref <blank_index>
|
102 |
-
min_decode_ratio: !ref <min_decode_ratio>
|
103 |
-
max_decode_ratio: !ref <max_decode_ratio>
|
104 |
-
beam_size: !ref <beam_size>
|
105 |
-
eos_threshold: !ref <eos_threshold>
|
106 |
-
using_max_attn_shift: !ref <using_max_attn_shift>
|
107 |
-
max_attn_shift: !ref <max_attn_shift>
|
108 |
-
temperature: !ref <temperature>
|
109 |
-
|
110 |
-
modules:
|
111 |
-
encoder: !ref <encoder>
|
112 |
-
decoder: !ref <decoder>
|
113 |
-
|
114 |
-
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
|
115 |
-
loadables:
|
116 |
-
wav2vec2: !ref <wav2vec2>
|
117 |
-
asr: !ref <asr_model>
|
118 |
-
tokenizer: !ref <tokenizer>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|