End of training
Browse files- README.md +2 -11
- generation_config.json +1 -1
README.md
CHANGED
|
@@ -6,8 +6,6 @@ base_model: openai/whisper-base
|
|
| 6 |
tags:
|
| 7 |
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
| 9 |
-
datasets:
|
| 10 |
-
- common_voice_16_1
|
| 11 |
model-index:
|
| 12 |
- name: ft_model
|
| 13 |
results: []
|
|
@@ -19,9 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# ft_model
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.5946
|
| 24 |
-
- Cer: 16.1162
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -42,7 +37,7 @@ More information needed
|
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 1e-05
|
| 44 |
- train_batch_size: 1
|
| 45 |
-
- eval_batch_size:
|
| 46 |
- seed: 42
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
|
@@ -52,15 +47,11 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
-
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 56 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 57 |
-
| 0.7715 | 0.05 | 1000 | 0.6407 | 19.5562 |
|
| 58 |
-
| 0.4602 | 0.1 | 2000 | 0.5946 | 16.1162 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
-
- Transformers 4.
|
| 64 |
- Pytorch 2.1.0+cu121
|
| 65 |
- Datasets 2.16.1
|
| 66 |
- Tokenizers 0.15.0
|
|
|
|
| 6 |
tags:
|
| 7 |
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: ft_model
|
| 11 |
results: []
|
|
|
|
| 17 |
# ft_model
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice dataset.
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 1e-05
|
| 39 |
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
|
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
+
- Transformers 4.38.0.dev0
|
| 55 |
- Pytorch 2.1.0+cu121
|
| 56 |
- Datasets 2.16.1
|
| 57 |
- Tokenizers 0.15.0
|
generation_config.json
CHANGED
|
@@ -251,5 +251,5 @@
|
|
| 251 |
"transcribe": 50359,
|
| 252 |
"translate": 50358
|
| 253 |
},
|
| 254 |
-
"transformers_version": "4.
|
| 255 |
}
|
|
|
|
| 251 |
"transcribe": 50359,
|
| 252 |
"translate": 50358
|
| 253 |
},
|
| 254 |
+
"transformers_version": "4.38.0.dev0"
|
| 255 |
}
|