wav2vec2-large-mms-1b-barwar
Browse files- README.md +109 -0
- adapter.aii.safetensors +3 -0
- preprocessor_config.json +9 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: facebook/mms-1b-all
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- nena_speech_1_0_test
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: wav2vec2-large-mms-1b-barwar
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: nena_speech_1_0_test
|
18 |
+
type: nena_speech_1_0_test
|
19 |
+
config: barwar
|
20 |
+
split: test
|
21 |
+
args: barwar
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 1.0
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# wav2vec2-large-mms-1b-barwar
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the nena_speech_1_0_test dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 3.4355
|
36 |
+
- Wer: 1.0
|
37 |
+
- Cer: 0.3295
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 0.001
|
57 |
+
- train_batch_size: 32
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 100
|
63 |
+
- num_epochs: 5
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
69 |
+
| 16.2134 | 0.15 | 25 | 17.6705 | 1.0 | 1.1562 |
|
70 |
+
| 6.1907 | 0.3 | 50 | 4.2262 | 0.9815 | 0.9986 |
|
71 |
+
| 3.6438 | 0.45 | 75 | 4.1625 | 1.0 | 0.7804 |
|
72 |
+
| 3.1627 | 0.6 | 100 | 4.1537 | 1.0 | 0.4727 |
|
73 |
+
| 2.2322 | 0.75 | 125 | 3.8028 | 1.0 | 0.4554 |
|
74 |
+
| 3.0705 | 0.9 | 150 | 3.3680 | 1.0 | 0.4352 |
|
75 |
+
| 2.9176 | 1.05 | 175 | 3.2934 | 1.0 | 0.4279 |
|
76 |
+
| 2.2255 | 1.2 | 200 | 3.6359 | 1.0 | 0.3926 |
|
77 |
+
| 2.4518 | 1.35 | 225 | 3.2249 | 1.0 | 0.3863 |
|
78 |
+
| 1.9254 | 1.5 | 250 | 3.7029 | 1.0 | 0.3875 |
|
79 |
+
| 2.7212 | 1.65 | 275 | 3.5201 | 1.0 | 0.3673 |
|
80 |
+
| 2.7976 | 1.8 | 300 | 3.3253 | 1.0 | 0.3986 |
|
81 |
+
| 2.0545 | 1.95 | 325 | 3.6138 | 1.0 | 0.3554 |
|
82 |
+
| 2.3335 | 2.1 | 350 | 3.5161 | 1.0 | 0.3554 |
|
83 |
+
| 2.0049 | 2.25 | 375 | 3.4727 | 1.0 | 0.3543 |
|
84 |
+
| 2.8896 | 2.4 | 400 | 3.2484 | 1.0 | 0.3535 |
|
85 |
+
| 1.9641 | 2.54 | 425 | 3.4330 | 1.0 | 0.3485 |
|
86 |
+
| 1.9649 | 2.69 | 450 | 3.8596 | 1.0 | 0.3444 |
|
87 |
+
| 2.0422 | 2.84 | 475 | 3.4291 | 1.0 | 0.3506 |
|
88 |
+
| 2.4093 | 2.99 | 500 | 3.3137 | 1.0 | 0.3434 |
|
89 |
+
| 1.8187 | 3.14 | 525 | 3.4423 | 1.0 | 0.3415 |
|
90 |
+
| 1.7495 | 3.29 | 550 | 3.5614 | 1.0 | 0.3431 |
|
91 |
+
| 2.0658 | 3.44 | 575 | 3.0324 | 1.0 | 0.3543 |
|
92 |
+
| 1.5128 | 3.59 | 600 | 3.6654 | 1.0 | 0.3452 |
|
93 |
+
| 1.7876 | 3.74 | 625 | 3.8747 | 1.0 | 0.3388 |
|
94 |
+
| 3.8652 | 3.89 | 650 | 2.9874 | 1.0 | 0.3387 |
|
95 |
+
| 2.8945 | 4.04 | 675 | 3.3015 | 1.0 | 0.3344 |
|
96 |
+
| 1.9763 | 4.19 | 700 | 3.1970 | 1.0 | 0.3389 |
|
97 |
+
| 2.0538 | 4.34 | 725 | 3.4811 | 1.0 | 0.3316 |
|
98 |
+
| 1.7723 | 4.49 | 750 | 3.6706 | 1.0 | 0.3305 |
|
99 |
+
| 2.0489 | 4.64 | 775 | 3.4281 | 1.0 | 0.3312 |
|
100 |
+
| 2.555 | 4.79 | 800 | 3.2610 | 1.0 | 0.3341 |
|
101 |
+
| 1.6591 | 4.94 | 825 | 3.4355 | 1.0 | 0.3295 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- Transformers 4.34.1
|
107 |
+
- Pytorch 2.1.0+cu121
|
108 |
+
- Datasets 2.14.6
|
109 |
+
- Tokenizers 0.14.1
|
adapter.aii.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203a3b1554682f21999462d60cf615185c1dbc3b2daaaceedf066695541e8aed
|
3 |
+
size 8952268
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35d648d7fa0c722151b532a48c6fcbf68373b37f5f3997d4aaeffd458bd55ef7
|
3 |
+
size 4536
|