update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,41 +1,38 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- el
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
-
- whisper-event
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
metrics:
|
| 11 |
- wer
|
| 12 |
model-index:
|
| 13 |
-
- name:
|
| 14 |
results:
|
| 15 |
- task:
|
| 16 |
name: Automatic Speech Recognition
|
| 17 |
type: automatic-speech-recognition
|
| 18 |
dataset:
|
| 19 |
-
name:
|
| 20 |
-
type:
|
| 21 |
config: el
|
| 22 |
split: test
|
| 23 |
args: el
|
| 24 |
metrics:
|
| 25 |
- name: Wer
|
| 26 |
type: wer
|
| 27 |
-
value: 9.
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 31 |
should probably proofread and complete it, then remove this comment. -->
|
| 32 |
|
| 33 |
-
#
|
| 34 |
|
| 35 |
-
This model is a fine-tuned version of [emilios/whisper-medium-el-n2](https://huggingface.co/emilios/whisper-medium-el-n2) on the
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
- Loss: 0.5669
|
| 38 |
-
- Wer: 9.
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
@@ -62,7 +59,7 @@ 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 |
|
| 67 |
### Training results
|
| 68 |
|
|
@@ -78,6 +75,7 @@ The following hyperparameters were used during training:
|
|
| 78 |
| 0.0001 | 469.94 | 8000 | 0.5669 | 9.8997 |
|
| 79 |
| 0.0001 | 528.76 | 9000 | 0.5645 | 9.9276 |
|
| 80 |
| 0.0001 | 587.82 | 10000 | 0.5674 | 9.9647 |
|
|
|
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
+
- common_voice_11_0
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
+
- name: emilios/whisper-medium-el-n2
|
| 11 |
results:
|
| 12 |
- task:
|
| 13 |
name: Automatic Speech Recognition
|
| 14 |
type: automatic-speech-recognition
|
| 15 |
dataset:
|
| 16 |
+
name: common_voice_11_0
|
| 17 |
+
type: common_voice_11_0
|
| 18 |
config: el
|
| 19 |
split: test
|
| 20 |
args: el
|
| 21 |
metrics:
|
| 22 |
- name: Wer
|
| 23 |
type: wer
|
| 24 |
+
value: 9.946136701337295
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
|
| 30 |
+
# emilios/whisper-medium-el-n2
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [emilios/whisper-medium-el-n2](https://huggingface.co/emilios/whisper-medium-el-n2) on the common_voice_11_0 dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
- Loss: 0.5669
|
| 35 |
+
- Wer: 9.9461
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
- lr_scheduler_type: linear
|
| 61 |
- lr_scheduler_warmup_steps: 500
|
| 62 |
+
- training_steps: 11000
|
| 63 |
|
| 64 |
### Training results
|
| 65 |
|
|
|
|
| 75 |
| 0.0001 | 469.94 | 8000 | 0.5669 | 9.8997 |
|
| 76 |
| 0.0001 | 528.76 | 9000 | 0.5645 | 9.9276 |
|
| 77 |
| 0.0001 | 587.82 | 10000 | 0.5674 | 9.9647 |
|
| 78 |
+
| 0.0003 | 646.82 | 11000 | 0.5669 | 9.9461 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|