Commit
•
eee6244
1
Parent(s):
7a3d2eb
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,39 +1,31 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
-
-
|
| 7 |
-
metrics:
|
| 8 |
-
- wer
|
| 9 |
model-index:
|
| 10 |
-
- name: whisper-large-v2-french
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Automatic Speech Recognition
|
| 14 |
-
type: automatic-speech-recognition
|
| 15 |
-
dataset:
|
| 16 |
-
name: voxpopuli
|
| 17 |
-
type: voxpopuli
|
| 18 |
-
config: fr
|
| 19 |
-
split: test
|
| 20 |
-
args: fr
|
| 21 |
-
metrics:
|
| 22 |
-
- name: Wer
|
| 23 |
-
type: wer
|
| 24 |
-
value: 0.10414829788606697
|
| 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 |
-
# whisper-large-v2-french
|
| 31 |
|
| 32 |
-
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
-
|
| 35 |
-
-
|
| 36 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -63,15 +55,6 @@ The following hyperparameters were used during training:
|
|
| 63 |
- lr_scheduler_warmup_steps: 50
|
| 64 |
- num_epochs: 3
|
| 65 |
|
| 66 |
-
### Training results
|
| 67 |
-
|
| 68 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
| 69 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
| 70 |
-
| 0.1851 | 1.0 | 2207 | 0.2349 | 0.1399 | 0.1044 |
|
| 71 |
-
| 0.1318 | 2.0 | 4415 | 0.2312 | 0.1377 | 0.1015 |
|
| 72 |
-
| 0.0921 | 3.0 | 6621 | 0.2468 | 0.1405 | 0.1041 |
|
| 73 |
-
|
| 74 |
-
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
- Transformers 4.30.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- fr
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
+
- mozilla-foundation/common_voice_13_0
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
+
- name: whisper-large-v2-french-2
|
| 11 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
# whisper-large-v2-french-2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the COMMON_VOICE_13_0 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- eval_loss: 0.2931
|
| 22 |
+
- eval_wer_ortho: 0.1809
|
| 23 |
+
- eval_wer: 0.1322
|
| 24 |
+
- eval_runtime: 19643.029
|
| 25 |
+
- eval_samples_per_second: 0.82
|
| 26 |
+
- eval_steps_per_second: 0.41
|
| 27 |
+
- epoch: 2.0
|
| 28 |
+
- step: 4190
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 55 |
- lr_scheduler_warmup_steps: 50
|
| 56 |
- num_epochs: 3
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
- Transformers 4.30.0.dev0
|