warmestman
commited on
Commit
•
f481a40
1
Parent(s):
e6ab416
End of training
Browse files- README.md +13 -12
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -8,36 +8,35 @@ tags:
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- mozilla-foundation/common_voice_16_1
|
11 |
-
- google/fleurs
|
12 |
metrics:
|
13 |
- wer
|
14 |
model-index:
|
15 |
-
- name: Whisper
|
16 |
results:
|
17 |
- task:
|
18 |
name: Automatic Speech Recognition
|
19 |
type: automatic-speech-recognition
|
20 |
dataset:
|
21 |
-
name: Common Voice 16.1
|
22 |
type: mozilla-foundation/common_voice_16_1
|
23 |
config: mn
|
24 |
-
split:
|
25 |
args: 'config: mn, split: test+validation'
|
26 |
metrics:
|
27 |
- name: Wer
|
28 |
type: wer
|
29 |
-
value:
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
33 |
should probably proofread and complete it, then remove this comment. -->
|
34 |
|
35 |
-
# Whisper
|
36 |
|
37 |
-
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 16.1
|
38 |
It achieves the following results on the evaluation set:
|
39 |
-
- Loss: 0.
|
40 |
-
- Wer:
|
41 |
|
42 |
## Model description
|
43 |
|
@@ -62,15 +61,17 @@ The following hyperparameters were used during training:
|
|
62 |
- seed: 42
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: linear
|
65 |
-
- lr_scheduler_warmup_steps:
|
66 |
-
- training_steps:
|
67 |
- mixed_precision_training: Native AMP
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
73 |
-
| 0.
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- mozilla-foundation/common_voice_16_1
|
|
|
11 |
metrics:
|
12 |
- wer
|
13 |
model-index:
|
14 |
+
- name: 'Whisper Small MN - Ankhbayasgalan Davaadorj '
|
15 |
results:
|
16 |
- task:
|
17 |
name: Automatic Speech Recognition
|
18 |
type: automatic-speech-recognition
|
19 |
dataset:
|
20 |
+
name: Common Voice 16.1
|
21 |
type: mozilla-foundation/common_voice_16_1
|
22 |
config: mn
|
23 |
+
split: test
|
24 |
args: 'config: mn, split: test+validation'
|
25 |
metrics:
|
26 |
- name: Wer
|
27 |
type: wer
|
28 |
+
value: 67.84162771514984
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
should probably proofread and complete it, then remove this comment. -->
|
33 |
|
34 |
+
# Whisper Small MN - Ankhbayasgalan Davaadorj
|
35 |
|
36 |
+
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 16.1 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.5096
|
39 |
+
- Wer: 67.8416
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
61 |
- seed: 42
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 500
|
65 |
+
- training_steps: 3000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
72 |
+
| 0.0832 | 3.94 | 1000 | 0.3988 | 73.6211 |
|
73 |
+
| 0.0051 | 7.87 | 2000 | 0.4563 | 66.0654 |
|
74 |
+
| 0.0004 | 11.81 | 3000 | 0.5096 | 67.8416 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:251938c11d5bfca4c98a1801d66c846319a6d84858176ac07698aa7a96410ccc
|
3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28e6dda3318792106e6dafc0ea5b7cca313d19f34a5029a6e42894c6fdb80445
|
3 |
size 1180663192
|