update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mascir_fr_wav2vec_version1000
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# mascir_fr_wav2vec_version1000
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4441
|
| 21 |
+
- Wer: 0.3622
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- num_epochs: 50
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| No log | 2.0 | 250 | 4.6558 | 1.0 |
|
| 54 |
+
| 5.4653 | 4.0 | 500 | 3.1189 | 1.0 |
|
| 55 |
+
| 5.4653 | 6.0 | 750 | 1.3807 | 0.9344 |
|
| 56 |
+
| 1.6415 | 8.0 | 1000 | 0.6832 | 0.5689 |
|
| 57 |
+
| 1.6415 | 10.0 | 1250 | 0.4986 | 0.48 |
|
| 58 |
+
| 0.3065 | 12.0 | 1500 | 0.4968 | 0.4711 |
|
| 59 |
+
| 0.3065 | 14.0 | 1750 | 0.4470 | 0.4533 |
|
| 60 |
+
| 0.1441 | 16.0 | 2000 | 0.4832 | 0.4433 |
|
| 61 |
+
| 0.1441 | 18.0 | 2250 | 0.5433 | 0.45 |
|
| 62 |
+
| 0.0938 | 20.0 | 2500 | 0.4734 | 0.4344 |
|
| 63 |
+
| 0.0938 | 22.0 | 2750 | 0.4745 | 0.4111 |
|
| 64 |
+
| 0.0727 | 24.0 | 3000 | 0.4236 | 0.4044 |
|
| 65 |
+
| 0.0727 | 26.0 | 3250 | 0.4692 | 0.4133 |
|
| 66 |
+
| 0.0556 | 28.0 | 3500 | 0.4411 | 0.3967 |
|
| 67 |
+
| 0.0556 | 30.0 | 3750 | 0.4722 | 0.3822 |
|
| 68 |
+
| 0.0422 | 32.0 | 4000 | 0.4845 | 0.3978 |
|
| 69 |
+
| 0.0422 | 34.0 | 4250 | 0.4818 | 0.4 |
|
| 70 |
+
| 0.0325 | 36.0 | 4500 | 0.4638 | 0.3944 |
|
| 71 |
+
| 0.0325 | 38.0 | 4750 | 0.4737 | 0.38 |
|
| 72 |
+
| 0.0284 | 40.0 | 5000 | 0.4615 | 0.3822 |
|
| 73 |
+
| 0.0284 | 42.0 | 5250 | 0.4491 | 0.3722 |
|
| 74 |
+
| 0.0235 | 44.0 | 5500 | 0.4480 | 0.3744 |
|
| 75 |
+
| 0.0235 | 46.0 | 5750 | 0.4630 | 0.3711 |
|
| 76 |
+
| 0.0172 | 48.0 | 6000 | 0.4421 | 0.3644 |
|
| 77 |
+
| 0.0172 | 50.0 | 6250 | 0.4441 | 0.3622 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.31.0
|
| 83 |
+
- Pytorch 2.0.1+cu118
|
| 84 |
+
- Datasets 2.14.2
|
| 85 |
+
- Tokenizers 0.13.3
|