End of training
Browse files- .ipynb_checkpoints/README-checkpoint.md +80 -0
- README.md +0 -2
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- et
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- whisper-event
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_11_0
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: Whisper Small et - Common Voice+FLEURS
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: Common Voice 11.0, FLEURS
|
20 |
+
type: mozilla-foundation/common_voice_11_0
|
21 |
+
config: null
|
22 |
+
split: None
|
23 |
+
metrics:
|
24 |
+
- name: Wer
|
25 |
+
type: wer
|
26 |
+
value: 42.48444526581655
|
27 |
+
---
|
28 |
+
|
29 |
+
|
30 |
+
# Whisper Small et - Common Voice+FLEURS
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0, FLEURS dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.8754
|
35 |
+
- Wer: 42.4844
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 1e-05
|
55 |
+
- train_batch_size: 64
|
56 |
+
- eval_batch_size: 32
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- lr_scheduler_warmup_steps: 500
|
61 |
+
- training_steps: 5000
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
68 |
+
| 0.0094 | 10.0 | 1000 | 0.7125 | 43.4085 |
|
69 |
+
| 0.0024 | 20.01 | 2000 | 0.7960 | 42.1795 |
|
70 |
+
| 0.0012 | 30.01 | 3000 | 0.8237 | 41.8961 |
|
71 |
+
| 0.0006 | 40.02 | 4000 | 0.8627 | 41.7853 |
|
72 |
+
| 0.0004 | 51.0 | 5000 | 0.8754 | 42.4844 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.26.0.dev0
|
78 |
+
- Pytorch 1.13.0+cu117
|
79 |
+
- Datasets 2.7.1.dev0
|
80 |
+
- Tokenizers 0.13.2
|
README.md
CHANGED
@@ -26,8 +26,6 @@ model-index:
|
|
26 |
value: 42.48444526581655
|
27 |
---
|
28 |
|
29 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
-
should probably proofread and complete it, then remove this comment. -->
|
31 |
|
32 |
# Whisper Small et - Common Voice+FLEURS
|
33 |
|
|
|
26 |
value: 42.48444526581655
|
27 |
---
|
28 |
|
|
|
|
|
29 |
|
30 |
# Whisper Small et - Common Voice+FLEURS
|
31 |
|