Model save
Browse files
README.md
CHANGED
|
@@ -1,27 +1,19 @@
|
|
| 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:
|
| 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 |
-
#
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.5102
|
| 24 |
-
- Cer: 31.4525
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -49,20 +41,6 @@ The following hyperparameters were used during training:
|
|
| 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 |
-
| 0.6644 | 0.48 | 1000 | 0.6600 | 42.3757 |
|
| 57 |
-
| 0.5769 | 0.97 | 2000 | 0.5747 | 35.0448 |
|
| 58 |
-
| 0.4652 | 1.45 | 3000 | 0.5467 | 32.5385 |
|
| 59 |
-
| 0.4504 | 1.93 | 4000 | 0.5234 | 32.5923 |
|
| 60 |
-
| 0.352 | 2.42 | 5000 | 0.5199 | 33.8982 |
|
| 61 |
-
| 0.3305 | 2.9 | 6000 | 0.5097 | 31.1140 |
|
| 62 |
-
| 0.2886 | 3.38 | 7000 | 0.5124 | 32.0912 |
|
| 63 |
-
| 0.2983 | 3.86 | 8000 | 0.5102 | 31.4525 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.34.0.dev0
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-base
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
+
- name: whisper-base-ko-callvoice
|
| 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 |
+
# whisper-base-ko-callvoice
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 41 |
- lr_scheduler_warmup_steps: 500
|
| 42 |
- training_steps: 8000
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.34.0.dev0
|