Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: mms-meta/mms-zeroshot-300m
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mms-zeroshot-bem-sv-male
|
| 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 |
+
# mms-zeroshot-bem-sv-male
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1876
|
| 22 |
+
- Wer: 0.3953
|
| 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: 0.0003
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 10.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| No log | 0.2183 | 200 | 2.3822 | 1.0 |
|
| 56 |
+
| No log | 0.4367 | 400 | 0.2715 | 0.5093 |
|
| 57 |
+
| 2.7769 | 0.6550 | 600 | 0.2489 | 0.4820 |
|
| 58 |
+
| 2.7769 | 0.8734 | 800 | 0.2296 | 0.4695 |
|
| 59 |
+
| 0.6809 | 1.0917 | 1000 | 0.2209 | 0.4638 |
|
| 60 |
+
| 0.6809 | 1.3100 | 1200 | 0.2163 | 0.4469 |
|
| 61 |
+
| 0.6809 | 1.5284 | 1400 | 0.2092 | 0.4400 |
|
| 62 |
+
| 0.6113 | 1.7467 | 1600 | 0.2047 | 0.4346 |
|
| 63 |
+
| 0.6113 | 1.9651 | 1800 | 0.2074 | 0.4467 |
|
| 64 |
+
| 0.5974 | 2.1834 | 2000 | 0.2041 | 0.4304 |
|
| 65 |
+
| 0.5974 | 2.4017 | 2200 | 0.2054 | 0.4317 |
|
| 66 |
+
| 0.5974 | 2.6201 | 2400 | 0.1987 | 0.4240 |
|
| 67 |
+
| 0.5636 | 2.8384 | 2600 | 0.2003 | 0.4252 |
|
| 68 |
+
| 0.5636 | 3.0568 | 2800 | 0.1997 | 0.4287 |
|
| 69 |
+
| 0.5398 | 3.2751 | 3000 | 0.2097 | 0.4400 |
|
| 70 |
+
| 0.5398 | 3.4934 | 3200 | 0.1968 | 0.4165 |
|
| 71 |
+
| 0.5398 | 3.7118 | 3400 | 0.2013 | 0.4218 |
|
| 72 |
+
| 0.5334 | 3.9301 | 3600 | 0.2003 | 0.4230 |
|
| 73 |
+
| 0.5334 | 4.1485 | 3800 | 0.1976 | 0.4227 |
|
| 74 |
+
| 0.5123 | 4.3668 | 4000 | 0.1978 | 0.4198 |
|
| 75 |
+
| 0.5123 | 4.5852 | 4200 | 0.2019 | 0.4298 |
|
| 76 |
+
| 0.5123 | 4.8035 | 4400 | 0.1939 | 0.4146 |
|
| 77 |
+
| 0.5119 | 5.0218 | 4600 | 0.1989 | 0.4161 |
|
| 78 |
+
| 0.5119 | 5.2402 | 4800 | 0.1902 | 0.4076 |
|
| 79 |
+
| 0.4929 | 5.4585 | 5000 | 0.1929 | 0.4116 |
|
| 80 |
+
| 0.4929 | 5.6769 | 5200 | 0.1943 | 0.4144 |
|
| 81 |
+
| 0.4929 | 5.8952 | 5400 | 0.1922 | 0.4106 |
|
| 82 |
+
| 0.4878 | 6.1135 | 5600 | 0.1933 | 0.4137 |
|
| 83 |
+
| 0.4878 | 6.3319 | 5800 | 0.1920 | 0.4058 |
|
| 84 |
+
| 0.4755 | 6.5502 | 6000 | 0.1927 | 0.4171 |
|
| 85 |
+
| 0.4755 | 6.7686 | 6200 | 0.1920 | 0.4127 |
|
| 86 |
+
| 0.4755 | 6.9869 | 6400 | 0.1925 | 0.4061 |
|
| 87 |
+
| 0.475 | 7.2052 | 6600 | 0.1884 | 0.4058 |
|
| 88 |
+
| 0.475 | 7.4236 | 6800 | 0.1903 | 0.4070 |
|
| 89 |
+
| 0.4715 | 7.6419 | 7000 | 0.1882 | 0.3996 |
|
| 90 |
+
| 0.4715 | 7.8603 | 7200 | 0.1881 | 0.4033 |
|
| 91 |
+
| 0.4715 | 8.0786 | 7400 | 0.1885 | 0.4007 |
|
| 92 |
+
| 0.4575 | 8.2969 | 7600 | 0.1885 | 0.4016 |
|
| 93 |
+
| 0.4575 | 8.5153 | 7800 | 0.1888 | 0.4050 |
|
| 94 |
+
| 0.4611 | 8.7336 | 8000 | 0.1884 | 0.4046 |
|
| 95 |
+
| 0.4611 | 8.9520 | 8200 | 0.1881 | 0.3974 |
|
| 96 |
+
| 0.4611 | 9.1703 | 8400 | 0.1865 | 0.3956 |
|
| 97 |
+
| 0.4559 | 9.3886 | 8600 | 0.1875 | 0.3974 |
|
| 98 |
+
| 0.4559 | 9.6070 | 8800 | 0.1872 | 0.3996 |
|
| 99 |
+
| 0.4536 | 9.8253 | 9000 | 0.1876 | 0.3953 |
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
### Framework versions
|
| 103 |
+
|
| 104 |
+
- Transformers 4.45.0.dev0
|
| 105 |
+
- Pytorch 2.4.0+cu121
|
| 106 |
+
- Datasets 2.21.0
|
| 107 |
+
- Tokenizers 0.19.1
|