bayartsogt
commited on
Commit
•
6c33ed0
1
Parent(s):
622096f
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice
|
7 |
+
model-index:
|
8 |
+
- name: wav2vec2-base-mn-scratch
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# wav2vec2-base-mn-scratch
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [bayartsogt/wav2vec2-base-mn-pretrain-42h](https://huggingface.co/bayartsogt/wav2vec2-base-mn-pretrain-42h) on the common_voice dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 2.8294
|
20 |
+
- eval_wer: 1.0026
|
21 |
+
- eval_cer: 0.7258
|
22 |
+
- eval_runtime: 173.2914
|
23 |
+
- eval_samples_per_second: 10.883
|
24 |
+
- eval_steps_per_second: 1.362
|
25 |
+
- epoch: 28.57
|
26 |
+
- step: 3600
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 16
|
47 |
+
- eval_batch_size: 8
|
48 |
+
- seed: 42
|
49 |
+
- gradient_accumulation_steps: 2
|
50 |
+
- total_train_batch_size: 32
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_steps: 500
|
54 |
+
- training_steps: 10000
|
55 |
+
- mixed_precision_training: Native AMP
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.20.1
|
60 |
+
- Pytorch 1.11.0
|
61 |
+
- Datasets 2.1.0
|
62 |
+
- Tokenizers 0.12.1
|