Model save
Browse files- README.md +69 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: config-0
|
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 |
+
# config-0
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7](https://huggingface.co/DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.8339
|
21 |
+
- Wer: 0.9455
|
22 |
+
- Cer: 0.5454
|
23 |
+
- Mer: 0.9402
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0003
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 100
|
51 |
+
- num_epochs: 40
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Mer |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
58 |
+
| 7.7805 | 1.0050 | 100 | 3.5031 | 1.0 | 1.0 | 1.0 |
|
59 |
+
| 3.4127 | 2.0101 | 200 | 3.4317 | 1.0 | 0.9381 | 1.0 |
|
60 |
+
| 3.3348 | 3.0151 | 300 | 3.2768 | 0.9999 | 0.9359 | 0.9999 |
|
61 |
+
| 2.763 | 4.0201 | 400 | 1.8339 | 0.9455 | 0.5454 | 0.9402 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.41.2
|
67 |
+
- Pytorch 2.3.0+cu121
|
68 |
+
- Datasets 2.20.0
|
69 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262242080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eaf2f047461c68d1b28635a3f199296b8389079dd32ff24052e4233beebb993
|
3 |
size 1262242080
|