|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: facebook/mms-1b-all |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_13_0 |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-large-mms-1b-fries-NL_common_voice_13b_other-train-validation |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: common_voice_13_0 |
|
type: common_voice_13_0 |
|
config: fy-NL |
|
split: test |
|
args: fy-NL |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.19910413556026252 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# wav2vec2-large-mms-1b-fries-NL_common_voice_13b_other-train-validation |
|
|
|
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_13_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1617 |
|
- Wer: 0.1991 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| No log | 0.01 | 200 | 0.2768 | 0.2969 | |
|
| 2.0359 | 0.03 | 400 | 0.2503 | 0.2754 | |
|
| 2.0359 | 0.04 | 600 | 0.2378 | 0.2671 | |
|
| 0.4005 | 0.06 | 800 | 0.2259 | 0.2572 | |
|
| 0.4005 | 0.07 | 1000 | 0.2387 | 0.2733 | |
|
| 0.4051 | 0.09 | 1200 | 0.2382 | 0.2645 | |
|
| 0.4051 | 0.1 | 1400 | 0.2231 | 0.2513 | |
|
| 0.3982 | 0.12 | 1600 | 0.2146 | 0.2470 | |
|
| 0.3982 | 0.13 | 1800 | 0.2167 | 0.2503 | |
|
| 0.3646 | 0.15 | 2000 | 0.2177 | 0.2499 | |
|
| 0.3646 | 0.16 | 2200 | 0.2228 | 0.2591 | |
|
| 0.3538 | 0.18 | 2400 | 0.2117 | 0.2445 | |
|
| 0.3538 | 0.19 | 2600 | 0.2097 | 0.2411 | |
|
| 0.3687 | 0.21 | 2800 | 0.2073 | 0.2425 | |
|
| 0.3687 | 0.22 | 3000 | 0.2138 | 0.2454 | |
|
| 0.3586 | 0.23 | 3200 | 0.2040 | 0.2375 | |
|
| 0.3586 | 0.25 | 3400 | 0.2059 | 0.2372 | |
|
| 0.3453 | 0.26 | 3600 | 0.2060 | 0.2397 | |
|
| 0.3453 | 0.28 | 3800 | 0.2015 | 0.2382 | |
|
| 0.3741 | 0.29 | 4000 | 0.2088 | 0.2457 | |
|
| 0.3741 | 0.31 | 4200 | 0.1948 | 0.2298 | |
|
| 0.3454 | 0.32 | 4400 | 0.2014 | 0.2342 | |
|
| 0.3454 | 0.34 | 4600 | 0.2031 | 0.2392 | |
|
| 0.351 | 0.35 | 4800 | 0.2018 | 0.2401 | |
|
| 0.351 | 0.37 | 5000 | 0.1962 | 0.2321 | |
|
| 0.3502 | 0.38 | 5200 | 0.1945 | 0.2323 | |
|
| 0.3502 | 0.4 | 5400 | 0.1956 | 0.2323 | |
|
| 0.3423 | 0.41 | 5600 | 0.1913 | 0.2266 | |
|
| 0.3423 | 0.43 | 5800 | 0.1921 | 0.2277 | |
|
| 0.3414 | 0.44 | 6000 | 0.1910 | 0.2262 | |
|
| 0.3414 | 0.45 | 6200 | 0.1891 | 0.2223 | |
|
| 0.3517 | 0.47 | 6400 | 0.1862 | 0.2230 | |
|
| 0.3517 | 0.48 | 6600 | 0.1879 | 0.2206 | |
|
| 0.3273 | 0.5 | 6800 | 0.1849 | 0.2176 | |
|
| 0.3273 | 0.51 | 7000 | 0.1845 | 0.2163 | |
|
| 0.321 | 0.53 | 7200 | 0.1831 | 0.2163 | |
|
| 0.321 | 0.54 | 7400 | 0.1825 | 0.2163 | |
|
| 0.321 | 0.56 | 7600 | 0.1797 | 0.2155 | |
|
| 0.321 | 0.57 | 7800 | 0.1787 | 0.2144 | |
|
| 0.3382 | 0.59 | 8000 | 0.1804 | 0.2132 | |
|
| 0.3382 | 0.6 | 8200 | 0.1789 | 0.2158 | |
|
| 0.3285 | 0.62 | 8400 | 0.1778 | 0.2130 | |
|
| 0.3285 | 0.63 | 8600 | 0.1753 | 0.2094 | |
|
| 0.3103 | 0.65 | 8800 | 0.1786 | 0.2147 | |
|
| 0.3103 | 0.66 | 9000 | 0.1799 | 0.2157 | |
|
| 0.3184 | 0.67 | 9200 | 0.1747 | 0.2098 | |
|
| 0.3184 | 0.69 | 9400 | 0.1740 | 0.2068 | |
|
| 0.3037 | 0.7 | 9600 | 0.1728 | 0.2090 | |
|
| 0.3037 | 0.72 | 9800 | 0.1732 | 0.2084 | |
|
| 0.3145 | 0.73 | 10000 | 0.1725 | 0.2085 | |
|
| 0.3145 | 0.75 | 10200 | 0.1691 | 0.2052 | |
|
| 0.3063 | 0.76 | 10400 | 0.1699 | 0.2062 | |
|
| 0.3063 | 0.78 | 10600 | 0.1694 | 0.2072 | |
|
| 0.3104 | 0.79 | 10800 | 0.1692 | 0.2063 | |
|
| 0.3104 | 0.81 | 11000 | 0.1674 | 0.2044 | |
|
| 0.2991 | 0.82 | 11200 | 0.1677 | 0.2040 | |
|
| 0.2991 | 0.84 | 11400 | 0.1664 | 0.2025 | |
|
| 0.3146 | 0.85 | 11600 | 0.1666 | 0.2011 | |
|
| 0.3146 | 0.87 | 11800 | 0.1666 | 0.2020 | |
|
| 0.3162 | 0.88 | 12000 | 0.1647 | 0.2009 | |
|
| 0.3162 | 0.89 | 12200 | 0.1642 | 0.2014 | |
|
| 0.3156 | 0.91 | 12400 | 0.1634 | 0.1997 | |
|
| 0.3156 | 0.92 | 12600 | 0.1630 | 0.1994 | |
|
| 0.3075 | 0.94 | 12800 | 0.1625 | 0.2009 | |
|
| 0.3075 | 0.95 | 13000 | 0.1621 | 0.1994 | |
|
| 0.3121 | 0.97 | 13200 | 0.1619 | 0.1989 | |
|
| 0.3121 | 0.98 | 13400 | 0.1619 | 0.1989 | |
|
| 0.2909 | 1.0 | 13600 | 0.1617 | 0.1991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0.dev0 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
