iulik-pisik
commited on
Commit
•
93672a7
1
Parent(s):
b76113a
End of training
Browse files
README.md
CHANGED
@@ -8,9 +8,24 @@ tags:
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- iulik-pisik/audio_vreme
|
|
|
|
|
11 |
model-index:
|
12 |
- name: Whisper Tiny Romanian - Vreme
|
13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -19,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
# Whisper Tiny Romanian - Vreme
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Vreme ProTv dataset.
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -47,6 +65,16 @@ The following hyperparameters were used during training:
|
|
47 |
- training_steps: 4000
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
### Framework versions
|
51 |
|
52 |
- Transformers 4.38.2
|
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- iulik-pisik/audio_vreme
|
11 |
+
metrics:
|
12 |
+
- wer
|
13 |
model-index:
|
14 |
- name: Whisper Tiny Romanian - Vreme
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Vreme ProTv
|
21 |
+
type: iulik-pisik/audio_vreme
|
22 |
+
config: default
|
23 |
+
split: None
|
24 |
+
args: 'config: ro, split: test'
|
25 |
+
metrics:
|
26 |
+
- name: Wer
|
27 |
+
type: wer
|
28 |
+
value: 13.912864775996711
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
# Whisper Tiny Romanian - Vreme
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Vreme ProTv dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.2668
|
39 |
+
- Wer: 13.9129
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
65 |
- training_steps: 4000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
72 |
+
| 0.0494 | 6.02 | 1000 | 0.1717 | 14.1184 |
|
73 |
+
| 0.0033 | 12.05 | 2000 | 0.2362 | 14.3855 |
|
74 |
+
| 0.0011 | 18.07 | 3000 | 0.2596 | 13.9540 |
|
75 |
+
| 0.0008 | 24.1 | 4000 | 0.2668 | 13.9129 |
|
76 |
+
|
77 |
+
|
78 |
### Framework versions
|
79 |
|
80 |
- Transformers 4.38.2
|
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 sha256:381304552af85fede58f4b512cce7a6a0e65dd71a530c63800c819a8191522da
|
3 |
size 151061672
|
runs/Mar16_16-15-07_9354793d2157/events.out.tfevents.1710605711.9354793d2157.793.0
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:dbcbc55b411469635078948ea91c2dec1fa8cc055ea433bb892d4739cd50848e
|
3 |
+
size 40759
|