update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,39 +1,38 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
- whisper-event
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
-
|
| 8 |
metrics:
|
| 9 |
- wer
|
| 10 |
model-index:
|
| 11 |
-
- name:
|
| 12 |
results:
|
| 13 |
- task:
|
| 14 |
name: Automatic Speech Recognition
|
| 15 |
type: automatic-speech-recognition
|
| 16 |
dataset:
|
| 17 |
-
name:
|
| 18 |
-
type:
|
| 19 |
config: ps_af
|
| 20 |
split: test
|
| 21 |
args: ps_af
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
-
value: 50.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
|
| 31 |
-
#
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 1.
|
| 36 |
-
- Wer: 50.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -60,8 +59,8 @@ The following hyperparameters were used during training:
|
|
| 60 |
- total_train_batch_size: 64
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
-
- lr_scheduler_warmup_steps:
|
| 64 |
-
- training_steps:
|
| 65 |
- mixed_precision_training: Native AMP
|
| 66 |
|
| 67 |
### Training results
|
|
@@ -78,6 +77,8 @@ The following hyperparameters were used during training:
|
|
| 78 |
| 0.0004 | 114.29 | 800 | 1.4382 | 50.4616 |
|
| 79 |
| 0.0004 | 128.57 | 900 | 1.4545 | 50.5297 |
|
| 80 |
| 0.0003 | 142.86 | 1000 | 1.4603 | 50.5675 |
|
|
|
|
|
|
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
+
- fleurs
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
+
- name: openai/whisper-medium
|
| 11 |
results:
|
| 12 |
- task:
|
| 13 |
name: Automatic Speech Recognition
|
| 14 |
type: automatic-speech-recognition
|
| 15 |
dataset:
|
| 16 |
+
name: fleurs
|
| 17 |
+
type: fleurs
|
| 18 |
config: ps_af
|
| 19 |
split: test
|
| 20 |
args: ps_af
|
| 21 |
metrics:
|
| 22 |
- name: Wer
|
| 23 |
type: wer
|
| 24 |
+
value: 50.544794188861985
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
|
| 30 |
+
# openai/whisper-medium
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the fleurs dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 1.4807
|
| 35 |
+
- Wer: 50.5448
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 59 |
- total_train_batch_size: 64
|
| 60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_steps: 10
|
| 63 |
+
- training_steps: 1200
|
| 64 |
- mixed_precision_training: Native AMP
|
| 65 |
|
| 66 |
### Training results
|
|
|
|
| 77 |
| 0.0004 | 114.29 | 800 | 1.4382 | 50.4616 |
|
| 78 |
| 0.0004 | 128.57 | 900 | 1.4545 | 50.5297 |
|
| 79 |
| 0.0003 | 142.86 | 1000 | 1.4603 | 50.5675 |
|
| 80 |
+
| 0.0003 | 157.14 | 1100 | 1.4750 | 50.5599 |
|
| 81 |
+
| 0.0003 | 171.43 | 1200 | 1.4807 | 50.5448 |
|
| 82 |
|
| 83 |
|
| 84 |
### Framework versions
|