Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: facebook/mms-1b-all
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-common_voice_20-hy-mms-finetune
|
| 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 |
+
# wav2vec2-common_voice_20-hy-mms-finetune
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1587
|
| 22 |
+
- Wer: 0.2464
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.001
|
| 42 |
+
- train_batch_size: 32
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 4.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 54 |
+
| No log | 0.2137 | 100 | 0.2269 | 0.3076 |
|
| 55 |
+
| No log | 0.4274 | 200 | 0.1915 | 0.2824 |
|
| 56 |
+
| No log | 0.6410 | 300 | 0.1993 | 0.2964 |
|
| 57 |
+
| No log | 0.8547 | 400 | 0.1832 | 0.2735 |
|
| 58 |
+
| 0.9965 | 1.0684 | 500 | 0.1764 | 0.2649 |
|
| 59 |
+
| 0.9965 | 1.2821 | 600 | 0.1733 | 0.2625 |
|
| 60 |
+
| 0.9965 | 1.4957 | 700 | 0.1725 | 0.2592 |
|
| 61 |
+
| 0.9965 | 1.7094 | 800 | 0.1706 | 0.2581 |
|
| 62 |
+
| 0.9965 | 1.9231 | 900 | 0.1681 | 0.2585 |
|
| 63 |
+
| 0.2922 | 2.1368 | 1000 | 0.1694 | 0.2591 |
|
| 64 |
+
| 0.2922 | 2.3504 | 1100 | 0.1701 | 0.2575 |
|
| 65 |
+
| 0.2922 | 2.5641 | 1200 | 0.1701 | 0.2614 |
|
| 66 |
+
| 0.2922 | 2.7778 | 1300 | 0.1654 | 0.2535 |
|
| 67 |
+
| 0.2922 | 2.9915 | 1400 | 0.1644 | 0.2517 |
|
| 68 |
+
| 0.2788 | 3.2051 | 1500 | 0.1636 | 0.2540 |
|
| 69 |
+
| 0.2788 | 3.4188 | 1600 | 0.1616 | 0.2512 |
|
| 70 |
+
| 0.2788 | 3.6325 | 1700 | 0.1600 | 0.2470 |
|
| 71 |
+
| 0.2788 | 3.8462 | 1800 | 0.1587 | 0.2464 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.51.0
|
| 77 |
+
- Pytorch 2.2.1+cu121
|
| 78 |
+
- Datasets 3.5.0
|
| 79 |
+
- Tokenizers 0.21.1
|