update model card README.md
Browse files
README.md
CHANGED
@@ -3,28 +3,14 @@ language:
|
|
3 |
- el
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
-
- hf-asr-leaderboard
|
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
10 |
-
metrics:
|
11 |
-
- wer
|
12 |
model-index:
|
13 |
- name: Whisper Medium El Greco
|
14 |
-
results:
|
15 |
-
- task:
|
16 |
-
name: Automatic Speech Recognition
|
17 |
-
type: automatic-speech-recognition
|
18 |
-
dataset:
|
19 |
-
name: Common Voice 11.0
|
20 |
-
type: mozilla-foundation/common_voice_11_0
|
21 |
-
config: el
|
22 |
-
split: test
|
23 |
-
args: el
|
24 |
-
metrics:
|
25 |
-
- name: Wer
|
26 |
-
type: wer
|
27 |
-
value: 10.74479940564636
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,8 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
-
|
38 |
-
-
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -64,19 +55,6 @@ The following hyperparameters were used during training:
|
|
64 |
- training_steps: 7000
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
-
### Training results
|
68 |
-
|
69 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
71 |
-
| 0.0039 | 2.49 | 1000 | 0.3787 | 12.4443 |
|
72 |
-
| 0.0017 | 4.98 | 2000 | 0.4010 | 12.2864 |
|
73 |
-
| 0.0006 | 7.46 | 3000 | 0.4108 | 11.6921 |
|
74 |
-
| 0.0004 | 9.95 | 4000 | 0.4221 | 11.5806 |
|
75 |
-
| 0.0005 | 12.44 | 5000 | 0.4222 | 11.4134 |
|
76 |
-
| 0.0006 | 4.03 | 6000 | 0.4230 | 10.9212 |
|
77 |
-
| 0.0006 | 9.03 | 7000 | 0.4245 | 10.7448 |
|
78 |
-
|
79 |
-
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.26.0.dev0
|
|
|
3 |
- el
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
+
- hf-asr-leaderboard, whisper-medium, mozilla-foundation/common_voice_11_0, greek,
|
7 |
+
whisper-event
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
11 |
model-index:
|
12 |
- name: Whisper Medium El Greco
|
13 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- eval_loss: 0.3854
|
24 |
+
- eval_wer: 11.4506
|
25 |
+
- eval_runtime: 1107.1212
|
26 |
+
- eval_samples_per_second: 1.532
|
27 |
+
- eval_steps_per_second: 0.096
|
28 |
+
- epoch: 33.98
|
29 |
+
- step: 7000
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
55 |
- training_steps: 7000
|
56 |
- mixed_precision_training: Native AMP
|
57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
### Framework versions
|
59 |
|
60 |
- Transformers 4.26.0.dev0
|