End of training
Browse files- README.md +35 -4
- model.safetensors +1 -1
README.md
CHANGED
@@ -5,9 +5,24 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- PolyAI/minds14
|
|
|
|
|
8 |
model-index:
|
9 |
- name: whisper-tiny-minds14
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,6 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# whisper-tiny-minds14
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,18 +53,30 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
- train_batch_size: 32
|
39 |
- eval_batch_size: 32
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: constant_with_warmup
|
43 |
-
- lr_scheduler_warmup_steps:
|
44 |
-
- training_steps:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- PolyAI/minds14
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
model-index:
|
11 |
- name: whisper-tiny-minds14
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: PolyAI/minds14
|
18 |
+
type: PolyAI/minds14
|
19 |
+
config: en-US
|
20 |
+
split: train
|
21 |
+
args: en-US
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.33412042502951594
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
# whisper-tiny-minds14
|
32 |
|
33 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4866
|
36 |
+
- Wer Ortho: 0.3356
|
37 |
+
- Wer: 0.3341
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 3e-05
|
57 |
- train_batch_size: 32
|
58 |
- eval_batch_size: 32
|
59 |
- seed: 42
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: constant_with_warmup
|
62 |
+
- lr_scheduler_warmup_steps: 5
|
63 |
+
- training_steps: 50
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
70 |
+
| 3.8369 | 0.36 | 5 | 2.6069 | 0.5200 | 0.4044 |
|
71 |
+
| 1.9739 | 0.71 | 10 | 1.0073 | 0.4411 | 0.4026 |
|
72 |
+
| 0.728 | 1.07 | 15 | 0.6096 | 0.3948 | 0.3902 |
|
73 |
+
| 0.3929 | 1.43 | 20 | 0.5288 | 0.4503 | 0.4486 |
|
74 |
+
| 0.4044 | 1.79 | 25 | 0.4995 | 0.3430 | 0.3430 |
|
75 |
+
| 0.311 | 2.14 | 30 | 0.4772 | 0.3701 | 0.3701 |
|
76 |
+
| 0.2404 | 2.5 | 35 | 0.4738 | 0.3134 | 0.3135 |
|
77 |
+
| 0.1688 | 2.86 | 40 | 0.4700 | 0.3257 | 0.3253 |
|
78 |
+
| 0.1278 | 3.21 | 45 | 0.4748 | 0.3183 | 0.3164 |
|
79 |
+
| 0.0775 | 3.57 | 50 | 0.4866 | 0.3356 | 0.3341 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:437792b312991a424fd96b7cd5ba655e24c4f6319968d703c260202490057632
|
3 |
size 151061672
|