Pushing language model
Browse files- README.md +107 -3
- added_tokens.json +4 -0
- alphabet.json +1 -0
- config.json +109 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +48 -0
- training_args.bin +3 -0
- vocab.json +40 -0
README.md
CHANGED
@@ -1,3 +1,107 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
3 |
+
license: apache-2.0
|
4 |
+
metrics:
|
5 |
+
- wer
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: bambara-5-hours-bambara-asr-hf
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# bambara-5-hours-bambara-asr-hf
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.8042
|
21 |
+
- Wer: 0.5257
|
22 |
+
- Cer: 0.2399
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0003
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 2
|
46 |
+
- total_train_batch_size: 32
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 500
|
50 |
+
- num_epochs: 50
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
56 |
+
| 5.6981 | 1.13 | 200 | 2.9919 | 1.0 | 1.0 |
|
57 |
+
| 2.9496 | 2.27 | 400 | 2.9333 | 1.0 | 1.0 |
|
58 |
+
| 2.4081 | 3.4 | 600 | 1.4375 | 0.8869 | 0.4174 |
|
59 |
+
| 1.5268 | 4.53 | 800 | 1.1942 | 0.7734 | 0.3602 |
|
60 |
+
| 1.3291 | 5.67 | 1000 | 1.1261 | 0.6712 | 0.2994 |
|
61 |
+
| 1.2301 | 6.8 | 1200 | 1.0859 | 0.6470 | 0.2892 |
|
62 |
+
| 1.1379 | 7.93 | 1400 | 1.0552 | 0.6314 | 0.2813 |
|
63 |
+
| 1.0664 | 9.07 | 1600 | 1.0684 | 0.6079 | 0.2731 |
|
64 |
+
| 0.9866 | 10.2 | 1800 | 1.0584 | 0.6110 | 0.2756 |
|
65 |
+
| 0.9625 | 11.33 | 2000 | 1.0776 | 0.5757 | 0.2590 |
|
66 |
+
| 0.8828 | 12.46 | 2200 | 1.1372 | 0.5865 | 0.2596 |
|
67 |
+
| 0.8451 | 13.6 | 2400 | 1.0821 | 0.5645 | 0.2574 |
|
68 |
+
| 0.8016 | 14.73 | 2600 | 1.1293 | 0.5754 | 0.2608 |
|
69 |
+
| 0.7615 | 15.86 | 2800 | 1.1312 | 0.5586 | 0.2519 |
|
70 |
+
| 0.715 | 17.0 | 3000 | 1.1657 | 0.5635 | 0.2558 |
|
71 |
+
| 0.6792 | 18.13 | 3200 | 1.2197 | 0.5521 | 0.2517 |
|
72 |
+
| 0.6498 | 19.26 | 3400 | 1.1157 | 0.5606 | 0.2533 |
|
73 |
+
| 0.6221 | 20.4 | 3600 | 1.2632 | 0.5501 | 0.2507 |
|
74 |
+
| 0.5912 | 21.53 | 3800 | 1.1686 | 0.5520 | 0.2505 |
|
75 |
+
| 0.5614 | 22.66 | 4000 | 1.3080 | 0.5547 | 0.2542 |
|
76 |
+
| 0.5485 | 23.8 | 4200 | 1.2349 | 0.5601 | 0.2583 |
|
77 |
+
| 0.5235 | 24.93 | 4400 | 1.2541 | 0.5458 | 0.2489 |
|
78 |
+
| 0.5084 | 26.06 | 4600 | 1.2414 | 0.5500 | 0.2514 |
|
79 |
+
| 0.4741 | 27.2 | 4800 | 1.5119 | 0.5444 | 0.2470 |
|
80 |
+
| 0.4699 | 28.33 | 5000 | 1.2778 | 0.5525 | 0.2524 |
|
81 |
+
| 0.4511 | 29.46 | 5200 | 1.5488 | 0.5502 | 0.2494 |
|
82 |
+
| 0.4181 | 30.59 | 5400 | 1.3489 | 0.5522 | 0.2536 |
|
83 |
+
| 0.4149 | 31.73 | 5600 | 1.5685 | 0.5460 | 0.2454 |
|
84 |
+
| 0.3998 | 32.86 | 5800 | 1.4369 | 0.5434 | 0.2494 |
|
85 |
+
| 0.401 | 33.99 | 6000 | 1.5961 | 0.5376 | 0.2433 |
|
86 |
+
| 0.3744 | 35.13 | 6200 | 1.5695 | 0.5361 | 0.2452 |
|
87 |
+
| 0.36 | 36.26 | 6400 | 1.5968 | 0.5400 | 0.2445 |
|
88 |
+
| 0.3435 | 37.39 | 6600 | 1.6238 | 0.5334 | 0.2424 |
|
89 |
+
| 0.3337 | 38.53 | 6800 | 1.6619 | 0.5340 | 0.2440 |
|
90 |
+
| 0.3232 | 39.66 | 7000 | 1.6444 | 0.5345 | 0.2446 |
|
91 |
+
| 0.3224 | 40.79 | 7200 | 1.7175 | 0.5417 | 0.2451 |
|
92 |
+
| 0.303 | 41.93 | 7400 | 1.6966 | 0.5273 | 0.2417 |
|
93 |
+
| 0.3028 | 43.06 | 7600 | 1.7403 | 0.5325 | 0.2431 |
|
94 |
+
| 0.2899 | 44.19 | 7800 | 1.7688 | 0.5255 | 0.2398 |
|
95 |
+
| 0.2861 | 45.33 | 8000 | 1.7705 | 0.5269 | 0.2405 |
|
96 |
+
| 0.2744 | 46.46 | 8200 | 1.7792 | 0.5244 | 0.2396 |
|
97 |
+
| 0.2731 | 47.59 | 8400 | 1.7876 | 0.5286 | 0.2412 |
|
98 |
+
| 0.27 | 48.73 | 8600 | 1.8060 | 0.5264 | 0.2403 |
|
99 |
+
| 0.2643 | 49.86 | 8800 | 1.8042 | 0.5257 | 0.2399 |
|
100 |
+
|
101 |
+
|
102 |
+
### Framework versions
|
103 |
+
|
104 |
+
- Transformers 4.38.1
|
105 |
+
- Pytorch 2.1.0+cu118
|
106 |
+
- Datasets 2.17.0
|
107 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 39,
|
3 |
+
"<s>": 38
|
4 |
+
}
|
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u00e1", "\u00e7", "\u00ea", "\u00ed", "\u00fa", "\u014b", "\u0254", "\u025b", "\u0272", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
config.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": true,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2ForCTC"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": true,
|
18 |
+
"conv_dim": [
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
3,
|
33 |
+
2,
|
34 |
+
2
|
35 |
+
],
|
36 |
+
"conv_stride": [
|
37 |
+
5,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
"ctc_loss_reduction": "mean",
|
46 |
+
"ctc_zero_infinity": true,
|
47 |
+
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": true,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_dropout": 0.0,
|
52 |
+
"feat_extract_norm": "layer",
|
53 |
+
"feat_proj_dropout": 0.1,
|
54 |
+
"feat_quantizer_dropout": 0.0,
|
55 |
+
"final_dropout": 0.0,
|
56 |
+
"gradient_checkpointing": false,
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.1,
|
59 |
+
"hidden_size": 1024,
|
60 |
+
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 4096,
|
62 |
+
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.1,
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_min_masks": 0,
|
66 |
+
"mask_feature_prob": 0.0,
|
67 |
+
"mask_time_length": 10,
|
68 |
+
"mask_time_min_masks": 2,
|
69 |
+
"mask_time_prob": 0.05,
|
70 |
+
"model_type": "wav2vec2",
|
71 |
+
"num_adapter_layers": 3,
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"output_hidden_size": 1024,
|
81 |
+
"pad_token_id": 37,
|
82 |
+
"proj_codevector_dim": 768,
|
83 |
+
"tdnn_dilation": [
|
84 |
+
1,
|
85 |
+
2,
|
86 |
+
3,
|
87 |
+
1,
|
88 |
+
1
|
89 |
+
],
|
90 |
+
"tdnn_dim": [
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
512,
|
94 |
+
512,
|
95 |
+
1500
|
96 |
+
],
|
97 |
+
"tdnn_kernel": [
|
98 |
+
5,
|
99 |
+
3,
|
100 |
+
3,
|
101 |
+
1,
|
102 |
+
1
|
103 |
+
],
|
104 |
+
"torch_dtype": "float32",
|
105 |
+
"transformers_version": "4.38.1",
|
106 |
+
"use_weighted_layer_sum": false,
|
107 |
+
"vocab_size": 40,
|
108 |
+
"xvector_output_dim": 512
|
109 |
+
}
|
language_model/5gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a2935b1b23655f32bf0b2f3152f5281180498b0e52c19ef6da1286a31ab7d58
|
3 |
+
size 16490821
|
language_model/attrs.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ca936a926f6dbac2954aa2a699459f3c4533bc27a3edb1919d9ad4032079d2c
|
3 |
+
size 1261971480
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"36": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"37": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"38": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"39": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b243d2f49a567b285ff56051e569a3d608ca76aa03cc8f4119b7fd2bb7bdaab8
|
3 |
+
size 4984
|
vocab.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 37,
|
3 |
+
"[UNK]": 36,
|
4 |
+
"a": 1,
|
5 |
+
"b": 2,
|
6 |
+
"c": 3,
|
7 |
+
"d": 4,
|
8 |
+
"e": 5,
|
9 |
+
"f": 6,
|
10 |
+
"g": 7,
|
11 |
+
"h": 8,
|
12 |
+
"i": 9,
|
13 |
+
"j": 10,
|
14 |
+
"k": 11,
|
15 |
+
"l": 12,
|
16 |
+
"m": 13,
|
17 |
+
"n": 14,
|
18 |
+
"o": 15,
|
19 |
+
"p": 16,
|
20 |
+
"q": 17,
|
21 |
+
"r": 18,
|
22 |
+
"s": 19,
|
23 |
+
"t": 20,
|
24 |
+
"u": 21,
|
25 |
+
"v": 22,
|
26 |
+
"w": 23,
|
27 |
+
"x": 24,
|
28 |
+
"y": 25,
|
29 |
+
"z": 26,
|
30 |
+
"|": 0,
|
31 |
+
"á": 27,
|
32 |
+
"ç": 28,
|
33 |
+
"ê": 29,
|
34 |
+
"í": 30,
|
35 |
+
"ú": 31,
|
36 |
+
"ŋ": 32,
|
37 |
+
"ɔ": 33,
|
38 |
+
"ɛ": 34,
|
39 |
+
"ɲ": 35
|
40 |
+
}
|