DewiBrynJones
commited on
Commit
•
782bf7c
1
Parent(s):
4c545bc
Model save
Browse files
README.md
CHANGED
@@ -3,24 +3,11 @@ license: apache-2.0
|
|
3 |
base_model: openai/whisper-large-v3
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean
|
8 |
metrics:
|
9 |
- wer
|
10 |
model-index:
|
11 |
- name: whisper-large-v3-ft-btb-cy
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Automatic Speech Recognition
|
15 |
-
type: automatic-speech-recognition
|
16 |
-
dataset:
|
17 |
-
name: DewiBrynJones/banc-trawsgrifiadau-bangor-clean default
|
18 |
-
type: DewiBrynJones/banc-trawsgrifiadau-bangor-clean
|
19 |
-
args: default
|
20 |
-
metrics:
|
21 |
-
- name: Wer
|
22 |
-
type: wer
|
23 |
-
value: 0.2817565771990433
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# whisper-large-v3-ft-btb-cy
|
30 |
|
31 |
-
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 0.
|
34 |
-
- Wer: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -66,11 +53,11 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
3 |
base_model: openai/whisper-large-v3
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- wer
|
8 |
model-index:
|
9 |
- name: whisper-large-v3-ft-btb-cy
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
|
16 |
# whisper-large-v3-ft-btb-cy
|
17 |
|
18 |
+
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5776
|
21 |
+
- Wer: 0.3064
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
56 |
+
| 0.3674 | 1.1390 | 1000 | 0.4709 | 0.3416 |
|
57 |
+
| 0.2228 | 2.2779 | 2000 | 0.4358 | 0.3117 |
|
58 |
+
| 0.1266 | 3.4169 | 3000 | 0.4588 | 0.3070 |
|
59 |
+
| 0.0611 | 4.5558 | 4000 | 0.5140 | 0.3039 |
|
60 |
+
| 0.0245 | 5.6948 | 5000 | 0.5776 | 0.3064 |
|
61 |
|
62 |
|
63 |
### Framework versions
|