End of training
Browse files
README.md
CHANGED
|
@@ -1,11 +1,28 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
| 4 |
metrics:
|
| 5 |
- wer
|
| 6 |
model-index:
|
| 7 |
- name: whisper_checkpoints
|
| 8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# whisper_checkpoints
|
| 15 |
|
| 16 |
-
This model
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.1501
|
| 19 |
- Wer: 10.8568
|
|
@@ -22,16 +39,6 @@ It achieves the following results on the evaluation set:
|
|
| 22 |
|
| 23 |
More information needed
|
| 24 |
|
| 25 |
-
## How to use
|
| 26 |
-
|
| 27 |
-
This model can be used with the `transformers` library as follows:
|
| 28 |
-
|
| 29 |
-
```python
|
| 30 |
-
from transformers import WhisperForConditionalGeneration, WhisperProcessor
|
| 31 |
-
|
| 32 |
-
model = WhisperForConditionalGeneration.from_pretrained("tmtms/whisper_checkpoints")
|
| 33 |
-
processor = WhisperProcessor.from_pretrained("tmtms/whisper_checkpoints")
|
| 34 |
-
|
| 35 |
## Intended uses & limitations
|
| 36 |
|
| 37 |
More information needed
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: INo0121/whisper-base-ko-callvoice
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- kresnik/zeroth_korean
|
| 10 |
metrics:
|
| 11 |
- wer
|
| 12 |
model-index:
|
| 13 |
- name: whisper_checkpoints
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Zeroth-Korean
|
| 20 |
+
type: kresnik/zeroth_korean
|
| 21 |
+
args: 'config: ko, split: test'
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 10.856798674898359
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# whisper_checkpoints
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [INo0121/whisper-base-ko-callvoice](https://huggingface.co/INo0121/whisper-base-ko-callvoice) on the Zeroth-Korean dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.1501
|
| 36 |
- Wer: 10.8568
|
|
|
|
| 39 |
|
| 40 |
More information needed
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
## Intended uses & limitations
|
| 43 |
|
| 44 |
More information needed
|