Model save
Browse files
README.md
CHANGED
|
@@ -1,12 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: openai/whisper-medium
|
| 3 |
-
datasets:
|
| 4 |
-
- Marcusxx/CngFSt10_5
|
| 5 |
-
language:
|
| 6 |
-
- ko
|
| 7 |
license: apache-2.0
|
|
|
|
| 8 |
tags:
|
| 9 |
-
- hf-asr-leaderboard
|
| 10 |
- generated_from_trainer
|
| 11 |
model-index:
|
| 12 |
- name: CngFSt10_5_sec_model
|
|
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# CngFSt10_5_sec_model
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Cer:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -47,18 +42,16 @@ The following hyperparameters were used during training:
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 500
|
| 50 |
-
- training_steps:
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 56 |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.0002 | 14.7059 | 4000 | 0.0074 | 23.4474 |
|
| 61 |
-
| 0.0001 | 18.3824 | 5000 | 0.0075 | 20.8184 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-medium
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: CngFSt10_5_sec_model
|
|
|
|
| 13 |
|
| 14 |
# CngFSt10_5_sec_model
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0068
|
| 19 |
+
- Cer: 22.2054
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_steps: 500
|
| 45 |
+
- training_steps: 3000
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 51 |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
| 52 |
+
| 0.0263 | 3.6765 | 1000 | 0.0404 | 52.6497 |
|
| 53 |
+
| 0.0009 | 7.3529 | 2000 | 0.0106 | 20.7149 |
|
| 54 |
+
| 0.0003 | 11.0294 | 3000 | 0.0068 | 22.2054 |
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
runs/Nov29_15-36-37_dev4.nectarsoft/events.out.tfevents.1732862202.dev4.nectarsoft.4101542.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e62304ef1f714293b595283d378cdebbd5a8e3f5c4d8da0c0b80c57d51eab7a6
|
| 3 |
+
size 32262
|