update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,15 +1,30 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- el
|
|
|
|
| 4 |
tags:
|
| 5 |
-
-
|
| 6 |
-
whisper-event
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: Whisper Medium El - Greek One
|
| 12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,7 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# Whisper Medium El - Greek One
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [openai/
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -40,17 +58,26 @@ The following hyperparameters were used during training:
|
|
| 40 |
- train_batch_size: 20
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
-
- gradient_accumulation_steps: 2
|
| 44 |
-
- total_train_batch_size: 40
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 500
|
| 48 |
-
- training_steps:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.26.0.dev0
|
| 54 |
-
- Pytorch 1.
|
| 55 |
- Datasets 2.7.1.dev0
|
| 56 |
- Tokenizers 0.13.2
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- el
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
+
- whisper-event
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
+
- mozilla-foundation/common_voice_11_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
model-index:
|
| 13 |
- name: Whisper Medium El - Greek One
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Common Voice 11.0
|
| 20 |
+
type: mozilla-foundation/common_voice_11_0
|
| 21 |
+
config: el
|
| 22 |
+
split: test
|
| 23 |
+
args: el
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Wer
|
| 26 |
+
type: wer
|
| 27 |
+
value: 13.976597325408619
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
# Whisper Medium El - Greek One
|
| 34 |
|
| 35 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
| 36 |
+
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.4707
|
| 38 |
+
- Wer: 13.9766
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
|
|
| 58 |
- train_batch_size: 20
|
| 59 |
- eval_batch_size: 8
|
| 60 |
- seed: 42
|
|
|
|
|
|
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_steps: 500
|
| 64 |
+
- training_steps: 5000
|
| 65 |
- mixed_precision_training: Native AMP
|
| 66 |
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 70 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 71 |
+
| 0.0036 | 10.01 | 1000 | 0.4461 | 15.9082 |
|
| 72 |
+
| 0.0001 | 20.02 | 2000 | 0.4250 | 14.5245 |
|
| 73 |
+
| 0.0 | 31.0 | 3000 | 0.4526 | 14.1902 |
|
| 74 |
+
| 0.0 | 41.01 | 4000 | 0.4657 | 14.1252 |
|
| 75 |
+
| 0.0 | 52.0 | 5000 | 0.4707 | 13.9766 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
### Framework versions
|
| 79 |
|
| 80 |
- Transformers 4.26.0.dev0
|
| 81 |
+
- Pytorch 1.13.0+cu117
|
| 82 |
- Datasets 2.7.1.dev0
|
| 83 |
- Tokenizers 0.13.2
|