Commit
•
c6476a8
1
Parent(s):
e87d0b9
End of training
Browse files- README.md +10 -16
- model.safetensors +1 -1
- runs/Dec06_21-56-04_ArtanisPC/events.out.tfevents.1701896174.ArtanisPC.786.4 +3 -0
- runs/Dec06_22-14-55_ArtanisPC/events.out.tfevents.1701897302.ArtanisPC.786.5 +3 -0
- runs/Dec06_23-37-57_ArtanisPC/events.out.tfevents.1701902281.ArtanisPC.786.6 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
-
|
4 |
license: apache-2.0
|
5 |
base_model: openai/whisper-small
|
6 |
tags:
|
@@ -21,11 +21,11 @@ model-index:
|
|
21 |
type: mozilla-foundation/common_voice_11_0
|
22 |
config: ro
|
23 |
split: test
|
24 |
-
args: 'config:
|
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 Romanian voice 1.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
-
- Wer:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -55,12 +55,10 @@ More information needed
|
|
55 |
### Training hyperparameters
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
-
- learning_rate:
|
59 |
- train_batch_size: 8
|
60 |
- eval_batch_size: 8
|
61 |
- seed: 42
|
62 |
-
- gradient_accumulation_steps: 2
|
63 |
-
- total_train_batch_size: 16
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
- lr_scheduler_warmup_steps: 250
|
@@ -71,14 +69,10 @@ The following hyperparameters were used during training:
|
|
71 |
|
72 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
73 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.1626 | 4.5 | 2500 | 0.2605 | 39.0530 |
|
79 |
-
| 0.1597 | 5.4 | 3000 | 0.2596 | 39.0745 |
|
80 |
-
| 0.1509 | 6.29 | 3500 | 0.2592 | 39.9276 |
|
81 |
-
| 0.1504 | 7.19 | 4000 | 0.2590 | 39.7591 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- ro
|
4 |
license: apache-2.0
|
5 |
base_model: openai/whisper-small
|
6 |
tags:
|
|
|
21 |
type: mozilla-foundation/common_voice_11_0
|
22 |
config: ro
|
23 |
split: test
|
24 |
+
args: 'config: ro, split: test'
|
25 |
metrics:
|
26 |
- name: Wer
|
27 |
type: wer
|
28 |
+
value: 42.218080149114634
|
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 Romanian voice 1.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.3430
|
39 |
+
- Wer: 42.2181
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
55 |
### Training hyperparameters
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 0.0001
|
59 |
- train_batch_size: 8
|
60 |
- eval_batch_size: 8
|
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: 250
|
|
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
72 |
+
| 0.396 | 0.9 | 1000 | 0.5565 | 88.6587 |
|
73 |
+
| 0.187 | 1.8 | 2000 | 0.4436 | 53.4841 |
|
74 |
+
| 0.0744 | 2.7 | 3000 | 0.3862 | 53.7279 |
|
75 |
+
| 0.0222 | 3.6 | 4000 | 0.3430 | 42.2181 |
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### 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 sha256:9add346e1ce142facf6af8eb1f24c7013ca8ea5052e61b212eb06bee34af46c9
|
3 |
size 966995080
|
runs/Dec06_21-56-04_ArtanisPC/events.out.tfevents.1701896174.ArtanisPC.786.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f75de8edfb502180760480ba06b492b895a4890f775d6a8a93cafe868f453d11
|
3 |
+
size 6565
|
runs/Dec06_22-14-55_ArtanisPC/events.out.tfevents.1701897302.ArtanisPC.786.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fabab1237da4d2d20971e4c017243ef2d42d65e2cef17731e38b7334fcd9516
|
3 |
+
size 15525
|
runs/Dec06_23-37-57_ArtanisPC/events.out.tfevents.1701902281.ArtanisPC.786.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0374a93c3ebe3027d5ea7a4f49786cece933e7bf097f19601b6aefe87e5c74e
|
3 |
+
size 31899
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c85cdc5000db92b6c5323f03fede29c47df56f7dfcc85d346d0940a16138f88
|
3 |
size 4856
|