update model card README.md
Browse files
README.md
CHANGED
|
@@ -7,9 +7,24 @@ tags:
|
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: Sussurrar
|
| 12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,6 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
# Sussurrar
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 11.0 dataset.
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -42,14 +60,23 @@ The following hyperparameters were used during training:
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
-
- training_steps:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- mozilla-foundation/common_voice_11_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
model-index:
|
| 13 |
- name: Sussurrar
|
| 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: pt
|
| 22 |
+
split: test
|
| 23 |
+
args: pt
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Wer
|
| 26 |
+
type: wer
|
| 27 |
+
value: 26.260504201680675
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
# Sussurrar
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 11.0 dataset.
|
| 36 |
+
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.4367
|
| 38 |
+
- Wer: 26.2605
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
|
|
| 60 |
- seed: 42
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
+
- training_steps: 2000
|
| 64 |
- mixed_precision_training: Native AMP
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 70 |
+
| 0.4076 | 0.1 | 200 | 0.5182 | 32.4930 |
|
| 71 |
+
| 0.3462 | 0.2 | 400 | 0.4912 | 29.0266 |
|
| 72 |
+
| 0.3283 | 0.3 | 600 | 0.4671 | 27.0308 |
|
| 73 |
+
| 0.3579 | 0.4 | 800 | 0.4662 | 26.6457 |
|
| 74 |
+
| 0.2766 | 0.5 | 1000 | 0.4639 | 26.7157 |
|
| 75 |
+
| 0.2147 | 1.03 | 1200 | 0.4470 | 26.7857 |
|
| 76 |
+
| 0.1877 | 1.13 | 1400 | 0.4382 | 26.4006 |
|
| 77 |
+
| 0.192 | 1.23 | 1600 | 0.4430 | 26.3655 |
|
| 78 |
+
| 0.1894 | 1.33 | 1800 | 0.4349 | 26.4006 |
|
| 79 |
+
| 0.1725 | 1.43 | 2000 | 0.4367 | 26.2605 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|