End of training
Browse files- README.md +25 -3
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -1,19 +1,27 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-base
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -41,6 +49,20 @@ The following hyperparameters were used during training:
|
|
| 41 |
- lr_scheduler_warmup_steps: 500
|
| 42 |
- training_steps: 8000
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.34.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: openai/whisper-base
|
| 6 |
tags:
|
| 7 |
+
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- INo0121/low_quality_call_voice
|
| 11 |
model-index:
|
| 12 |
+
- name: Whisper Base for Korean Low quaiity Call Voices
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
+
# Whisper Base for Korean Low quaiity Call Voices
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Korean Low Quaiity Call Voices dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4941
|
| 24 |
+
- Cer: 30.7538
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 49 |
- lr_scheduler_warmup_steps: 500
|
| 50 |
- training_steps: 8000
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 56 |
+
| 0.6416 | 0.44 | 1000 | 0.6564 | 64.1489 |
|
| 57 |
+
| 0.5914 | 0.88 | 2000 | 0.5688 | 37.4957 |
|
| 58 |
+
| 0.435 | 1.32 | 3000 | 0.5349 | 32.6734 |
|
| 59 |
+
| 0.4056 | 1.76 | 4000 | 0.5124 | 30.9065 |
|
| 60 |
+
| 0.3368 | 2.2 | 5000 | 0.5057 | 32.6925 |
|
| 61 |
+
| 0.3107 | 2.64 | 6000 | 0.4979 | 32.8315 |
|
| 62 |
+
| 0.3016 | 3.08 | 7000 | 0.4947 | 29.3060 |
|
| 63 |
+
| 0.2979 | 3.52 | 8000 | 0.4941 | 30.7538 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.34.0.dev0
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 290458785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62462e24b9f3e635ed87e13b29b48650d00fb7f996c600186c77489de4347350
|
| 3 |
size 290458785
|