Santiago Hincapie
commited on
Commit
•
e6b6953
1
Parent(s):
b78894c
feat: update model config
Browse files- added_tokens.json +0 -1
- config.json +0 -107
- preprocessor_config.json +0 -9
- pytorch_model.bin +0 -3
- run.sh +24 -22
- special_tokens_map.json +0 -1
- tokenizer_config.json +0 -1
- training_args.bin +0 -3
- vocab.json +0 -1
added_tokens.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"<s>": 37, "</s>": 38}
|
|
|
|
config.json
DELETED
@@ -1,107 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"adapter_kernel_size": 3,
|
5 |
-
"adapter_stride": 2,
|
6 |
-
"add_adapter": false,
|
7 |
-
"apply_spec_augment": true,
|
8 |
-
"architectures": [
|
9 |
-
"Wav2Vec2ForCTC"
|
10 |
-
],
|
11 |
-
"attention_dropout": 0.0,
|
12 |
-
"bos_token_id": 1,
|
13 |
-
"classifier_proj_size": 256,
|
14 |
-
"codevector_dim": 768,
|
15 |
-
"contrastive_logits_temperature": 0.1,
|
16 |
-
"conv_bias": true,
|
17 |
-
"conv_dim": [
|
18 |
-
512,
|
19 |
-
512,
|
20 |
-
512,
|
21 |
-
512,
|
22 |
-
512,
|
23 |
-
512,
|
24 |
-
512
|
25 |
-
],
|
26 |
-
"conv_kernel": [
|
27 |
-
10,
|
28 |
-
3,
|
29 |
-
3,
|
30 |
-
3,
|
31 |
-
3,
|
32 |
-
2,
|
33 |
-
2
|
34 |
-
],
|
35 |
-
"conv_stride": [
|
36 |
-
5,
|
37 |
-
2,
|
38 |
-
2,
|
39 |
-
2,
|
40 |
-
2,
|
41 |
-
2,
|
42 |
-
2
|
43 |
-
],
|
44 |
-
"ctc_loss_reduction": "mean",
|
45 |
-
"ctc_zero_infinity": false,
|
46 |
-
"diversity_loss_weight": 0.1,
|
47 |
-
"do_stable_layer_norm": true,
|
48 |
-
"eos_token_id": 2,
|
49 |
-
"feat_extract_activation": "gelu",
|
50 |
-
"feat_extract_dropout": 0.0,
|
51 |
-
"feat_extract_norm": "layer",
|
52 |
-
"feat_proj_dropout": 0.0,
|
53 |
-
"feat_quantizer_dropout": 0.0,
|
54 |
-
"final_dropout": 0.0,
|
55 |
-
"hidden_act": "gelu",
|
56 |
-
"hidden_dropout": 0.0,
|
57 |
-
"hidden_size": 1024,
|
58 |
-
"initializer_range": 0.02,
|
59 |
-
"intermediate_size": 4096,
|
60 |
-
"layer_norm_eps": 1e-05,
|
61 |
-
"layerdrop": 0.0,
|
62 |
-
"mask_feature_length": 64,
|
63 |
-
"mask_feature_min_masks": 0,
|
64 |
-
"mask_feature_prob": 0.25,
|
65 |
-
"mask_time_length": 10,
|
66 |
-
"mask_time_min_masks": 2,
|
67 |
-
"mask_time_prob": 0.75,
|
68 |
-
"model_type": "wav2vec2",
|
69 |
-
"num_adapter_layers": 3,
|
70 |
-
"num_attention_heads": 16,
|
71 |
-
"num_codevector_groups": 2,
|
72 |
-
"num_codevectors_per_group": 320,
|
73 |
-
"num_conv_pos_embedding_groups": 16,
|
74 |
-
"num_conv_pos_embeddings": 128,
|
75 |
-
"num_feat_extract_layers": 7,
|
76 |
-
"num_hidden_layers": 24,
|
77 |
-
"num_negatives": 100,
|
78 |
-
"output_hidden_size": 1024,
|
79 |
-
"pad_token_id": 36,
|
80 |
-
"proj_codevector_dim": 768,
|
81 |
-
"tdnn_dilation": [
|
82 |
-
1,
|
83 |
-
2,
|
84 |
-
3,
|
85 |
-
1,
|
86 |
-
1
|
87 |
-
],
|
88 |
-
"tdnn_dim": [
|
89 |
-
512,
|
90 |
-
512,
|
91 |
-
512,
|
92 |
-
512,
|
93 |
-
1500
|
94 |
-
],
|
95 |
-
"tdnn_kernel": [
|
96 |
-
5,
|
97 |
-
3,
|
98 |
-
3,
|
99 |
-
1,
|
100 |
-
1
|
101 |
-
],
|
102 |
-
"torch_dtype": "float32",
|
103 |
-
"transformers_version": "4.16.0.dev0",
|
104 |
-
"use_weighted_layer_sum": false,
|
105 |
-
"vocab_size": 39,
|
106 |
-
"xvector_output_dim": 512
|
107 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
preprocessor_config.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"do_normalize": true,
|
3 |
-
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
-
"feature_size": 1,
|
5 |
-
"padding_side": "right",
|
6 |
-
"padding_value": 0,
|
7 |
-
"return_attention_mask": true,
|
8 |
-
"sampling_rate": 16000
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:122d5480924adf4705e1f37e28c0c798df35e76a41767b73474d3d5df8c1062f
|
3 |
-
size 1262083569
|
|
|
|
|
|
|
|
run.sh
CHANGED
@@ -1,36 +1,38 @@
|
|
1 |
#!/bin/sh
|
2 |
|
3 |
export CUDA_VISIBLE_DEVICES=1,2
|
|
|
4 |
python src/run_speech_recognition_ctc_bnb.py \
|
5 |
--dataset_name="mozilla-foundation/common_voice_7_0" \
|
6 |
-
--model_name_or_path="facebook/wav2vec2-xls-r-
|
7 |
--dataset_config_name="et" \
|
8 |
--output_dir="./" \
|
9 |
--overwrite_output_dir \
|
10 |
-
--num_train_epochs=
|
11 |
-
--per_device_train_batch_size=
|
12 |
-
--per_device_eval_batch_size=
|
13 |
-
--gradient_accumulation_steps=
|
14 |
-
--learning_rate=
|
15 |
-
--save_total_limit=
|
16 |
-
--warmup_steps=
|
17 |
-
--evaluation_strategy=
|
18 |
-
--text_column_name=
|
19 |
-
--length_column_name=
|
20 |
-
--save_steps=
|
21 |
-
--eval_steps=
|
22 |
-
--logging_steps=
|
23 |
-
--layerdrop=
|
24 |
--freeze_feature_encoder \
|
25 |
-
--feat_proj_dropout=
|
26 |
-
--mask_time_prob="0.75" \
|
27 |
-
--mask_time_length="10" \
|
28 |
-
--mask_feature_prob="0.25" \
|
29 |
-
--mask_feature_length="64" \
|
30 |
--chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – \
|
31 |
--gradient_checkpointing \
|
32 |
-
--
|
33 |
--fp16 \
|
34 |
--group_by_length \
|
|
|
|
|
|
|
|
|
35 |
--do_train --do_eval \
|
36 |
-
--
|
|
|
|
1 |
#!/bin/sh
|
2 |
|
3 |
export CUDA_VISIBLE_DEVICES=1,2
|
4 |
+
|
5 |
python src/run_speech_recognition_ctc_bnb.py \
|
6 |
--dataset_name="mozilla-foundation/common_voice_7_0" \
|
7 |
+
--model_name_or_path="facebook/wav2vec2-xls-r-1b" \
|
8 |
--dataset_config_name="et" \
|
9 |
--output_dir="./" \
|
10 |
--overwrite_output_dir \
|
11 |
+
--num_train_epochs=100 \
|
12 |
+
--per_device_train_batch_size=32 \
|
13 |
+
--per_device_eval_batch_size=32 \
|
14 |
+
--gradient_accumulation_steps=2 \
|
15 |
+
--learning_rate=3e-4 \
|
16 |
+
--save_total_limit=3 \
|
17 |
+
--warmup_steps=500 \
|
18 |
+
--evaluation_strategy=steps \
|
19 |
+
--text_column_name=sentence \
|
20 |
+
--length_column_name=input_length \
|
21 |
+
--save_steps=500 \
|
22 |
+
--eval_steps=500 \
|
23 |
+
--logging_steps=100 \
|
24 |
+
--layerdrop=0.0 \
|
25 |
--freeze_feature_encoder \
|
26 |
+
--feat_proj_dropout=0.1 \
|
|
|
|
|
|
|
|
|
27 |
--chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – \
|
28 |
--gradient_checkpointing \
|
29 |
+
--lr_scheduler_type=cosine \
|
30 |
--fp16 \
|
31 |
--group_by_length \
|
32 |
+
--mask_time_prob=0.1 \
|
33 |
+
--mask_time_length=10 \
|
34 |
+
--report_to=wandb \
|
35 |
+
--run_name="cosine+drop_proj+low_specaugment-1b" \
|
36 |
--do_train --do_eval \
|
37 |
+
--use_auth_token \
|
38 |
+
--push_to_hub
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f3e82d9fe00fea24d2f00c4b477dbd5b91e33cea6ba3cf8903f298d8f42fefbe
|
3 |
-
size 2991
|
|
|
|
|
|
|
|
vocab.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "ä": 27, "õ": 28, "ö": 29, "ü": 30, "š": 31, "ž": 32, "̇": 33, "„": 34, "|": 0, "[UNK]": 35, "[PAD]": 36}
|
|
|
|