End of training
Browse files
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: openai/whisper-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- wer
|
| 8 |
model-index:
|
| 9 |
- name: small-Cotrsc
|
| 10 |
results: []
|
|
@@ -17,8 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -38,24 +41,15 @@ More information needed
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 1e-05
|
| 41 |
-
- train_batch_size:
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
-
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 54 |
-
| 0.0541 | 0.1763 | 1000 | 0.0507 | 39.0584 |
|
| 55 |
-
| 0.0391 | 0.3527 | 2000 | 0.0424 | 34.1483 |
|
| 56 |
-
| 0.037 | 0.5290 | 3000 | 0.0369 | 31.2588 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.41.2
|
|
|
|
| 3 |
base_model: openai/whisper-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: small-Cotrsc
|
| 8 |
results: []
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 0.0487
|
| 19 |
+
- eval_wer: 39.6655
|
| 20 |
+
- eval_runtime: 516.4929
|
| 21 |
+
- eval_samples_per_second: 0.67
|
| 22 |
+
- eval_steps_per_second: 0.085
|
| 23 |
+
- epoch: 0.4231
|
| 24 |
+
- step: 1200
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 1e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
- eval_batch_size: 8
|
| 46 |
- seed: 42
|
| 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: 1200
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.41.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233e95402024e35276310208eec63c745778d12942a289d776316f6517050157
|
| 3 |
size 966995080
|
runs/Jun04_17-00-06_c8b279491245/events.out.tfevents.1717520409.c8b279491245.34.0
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 sha256:678b775581bf5d7fe3d5c78efcf2c85f8d591fc956f8a59ed4162adac7545b42
|
| 3 |
+
size 8610
|