End of training
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Wer
|
27 |
type: wer
|
28 |
-
value:
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
-
- Wer:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -62,7 +62,7 @@ The following hyperparameters were used during training:
|
|
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:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
@@ -73,6 +73,10 @@ The following hyperparameters were used during training:
|
|
73 |
| 0.2452 | 0.8237 | 2000 | 0.3639 | 46.1863 |
|
74 |
| 0.1613 | 1.2356 | 3000 | 0.3470 | 44.9194 |
|
75 |
| 0.1382 | 1.6474 | 4000 | 0.3398 | 45.0351 |
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
25 |
metrics:
|
26 |
- name: Wer
|
27 |
type: wer
|
28 |
+
value: 44.396092688480046
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.3517
|
39 |
+
- Wer: 44.3961
|
40 |
|
41 |
## Model description
|
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: 8000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
|
|
73 |
| 0.2452 | 0.8237 | 2000 | 0.3639 | 46.1863 |
|
74 |
| 0.1613 | 1.2356 | 3000 | 0.3470 | 44.9194 |
|
75 |
| 0.1382 | 1.6474 | 4000 | 0.3398 | 45.0351 |
|
76 |
+
| 0.1177 | 2.0593 | 5000 | 0.3502 | 44.5154 |
|
77 |
+
| 0.1206 | 2.4712 | 6000 | 0.3501 | 44.9781 |
|
78 |
+
| 0.1216 | 2.8830 | 7000 | 0.3423 | 43.5258 |
|
79 |
+
| 0.072 | 3.2949 | 8000 | 0.3517 | 44.3961 |
|
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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0f5e6afa4e521dd2e670f1864bfa40d6d953a3fe8797943bdd709dce5f91415
|
3 |
size 966995080
|
runs/Oct07_05-12-14_8d8a2390d628/events.out.tfevents.1728278046.8d8a2390d628.4720.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:265b4a76beef093f3ce68c589f633b12ea7fae3d503723aa8d363ccb5493451a
|
3 |
+
size 41244
|