smutuvi/wav2vec2-large-xlsr-sw_ndizi_782_100_epoch
Browse files- README.md +83 -0
- added_tokens.json +4 -0
- model.safetensors +1 -1
- preprocessor_config.json +1 -0
- runs/Mar22_05-32-55_hades-prod01/events.out.tfevents.1711085640.hades-prod01.437015.0 +2 -2
- special_tokens_map.json +30 -0
- tokenizer_config.json +48 -0
- vocab.json +61 -0
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: smutuvi/wav2vec2-large-xlsr-sw
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-large-xlsr-sw_ndizi_782_100_epochs
|
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 |
+
# wav2vec2-large-xlsr-sw_ndizi_782_100_epochs
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [smutuvi/wav2vec2-large-xlsr-sw](https://huggingface.co/smutuvi/wav2vec2-large-xlsr-sw) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.1009
|
21 |
+
- Wer: 0.4847
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0003
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 8
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 100
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
56 |
+
| 1.4035 | 4.79 | 400 | 1.2492 | 0.5608 |
|
57 |
+
| 0.8489 | 9.58 | 800 | 1.0208 | 0.5114 |
|
58 |
+
| 0.632 | 14.37 | 1200 | 1.3292 | 0.5306 |
|
59 |
+
| 0.4653 | 19.16 | 1600 | 1.5159 | 0.5109 |
|
60 |
+
| 0.3598 | 23.95 | 2000 | 1.4650 | 0.5450 |
|
61 |
+
| 0.2776 | 28.74 | 2400 | 1.8568 | 0.5124 |
|
62 |
+
| 0.218 | 33.53 | 2800 | 2.0913 | 0.5188 |
|
63 |
+
| 0.1711 | 38.32 | 3200 | 2.2706 | 0.5035 |
|
64 |
+
| 0.141 | 43.11 | 3600 | 2.3050 | 0.5094 |
|
65 |
+
| 0.1162 | 47.9 | 4000 | 2.4539 | 0.5025 |
|
66 |
+
| 0.1007 | 52.69 | 4400 | 2.4754 | 0.5020 |
|
67 |
+
| 0.0881 | 57.49 | 4800 | 2.5512 | 0.5030 |
|
68 |
+
| 0.0816 | 62.28 | 5200 | 2.6458 | 0.5064 |
|
69 |
+
| 0.0792 | 67.07 | 5600 | 2.7869 | 0.5025 |
|
70 |
+
| 0.06 | 71.86 | 6000 | 2.9063 | 0.5040 |
|
71 |
+
| 0.0594 | 76.65 | 6400 | 2.8363 | 0.5049 |
|
72 |
+
| 0.0527 | 81.44 | 6800 | 3.0801 | 0.4921 |
|
73 |
+
| 0.0473 | 86.23 | 7200 | 3.0959 | 0.4867 |
|
74 |
+
| 0.0471 | 91.02 | 7600 | 3.0942 | 0.4852 |
|
75 |
+
| 0.0405 | 95.81 | 8000 | 3.1009 | 0.4847 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.37.1
|
81 |
+
- Pytorch 2.2.1+cu118
|
82 |
+
- Datasets 2.16.1
|
83 |
+
- Tokenizers 0.15.0
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 60,
|
3 |
+
"<s>": 59
|
4 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262057580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c061c03b90ba153cdd6765384ddb007ed10b0cdbcee804bc0a84865cc21ac33
|
3 |
size 1262057580
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
runs/Mar22_05-32-55_hades-prod01/events.out.tfevents.1711085640.hades-prod01.437015.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dff4db984a7efbc25a5d02f7ffe2167e23b33b2b295c8cb932c7e6c26e63477
|
3 |
+
size 15974
|
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 |
+
"57": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"58": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"59": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"60": {
|
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": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 35,
|
3 |
+
"(": 33,
|
4 |
+
")": 5,
|
5 |
+
"*": 52,
|
6 |
+
"/": 48,
|
7 |
+
"=": 44,
|
8 |
+
"[PAD]": 58,
|
9 |
+
"[UNK]": 57,
|
10 |
+
"_": 18,
|
11 |
+
"`": 6,
|
12 |
+
"a": 51,
|
13 |
+
"b": 16,
|
14 |
+
"c": 37,
|
15 |
+
"d": 28,
|
16 |
+
"e": 24,
|
17 |
+
"f": 54,
|
18 |
+
"g": 56,
|
19 |
+
"h": 30,
|
20 |
+
"i": 17,
|
21 |
+
"j": 3,
|
22 |
+
"k": 19,
|
23 |
+
"l": 47,
|
24 |
+
"m": 55,
|
25 |
+
"n": 23,
|
26 |
+
"o": 21,
|
27 |
+
"p": 1,
|
28 |
+
"q": 34,
|
29 |
+
"r": 50,
|
30 |
+
"s": 4,
|
31 |
+
"t": 0,
|
32 |
+
"u": 22,
|
33 |
+
"v": 26,
|
34 |
+
"w": 15,
|
35 |
+
"x": 2,
|
36 |
+
"y": 53,
|
37 |
+
"z": 11,
|
38 |
+
"|": 14,
|
39 |
+
"°": 43,
|
40 |
+
"µ": 46,
|
41 |
+
"á": 12,
|
42 |
+
"â": 41,
|
43 |
+
"ã": 45,
|
44 |
+
"å": 7,
|
45 |
+
"é": 36,
|
46 |
+
"ë": 49,
|
47 |
+
"í": 39,
|
48 |
+
"ï": 38,
|
49 |
+
"ñ": 13,
|
50 |
+
"ó": 9,
|
51 |
+
"ö": 29,
|
52 |
+
"ø": 27,
|
53 |
+
"ú": 40,
|
54 |
+
"š": 31,
|
55 |
+
"ū": 8,
|
56 |
+
"ː": 25,
|
57 |
+
"ụ": 10,
|
58 |
+
"’": 32,
|
59 |
+
"•": 42,
|
60 |
+
"…": 20
|
61 |
+
}
|