Downloads · 30 days
17
3% of all-time downloads
infinitejoy/wav2vec2-large-xls-r-300m-indonesian
wav2vec2-large-xls-r-300m-indonesian is a automatic speech recognition model from infinitejoy. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
17
3% of all-time downloads
All-time downloads
508
Public
Repo size
42.9 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - ID dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0387 | 4.72 | 1000 | 3.0892 | 1.0 |
| 1.7911 | 9.43 | 2000 | 0.8451 | 0.6702 |
| 1.2826 | 14.15 | 3000 | 0.4211 | 0.4166 |
| 1.1802 | 18.87 | 4000 | 0.3508 | 0.4690 |
| 1.1065 | 23.58 | 5000 | 0.3319 | 0.4662 |
| 1.0921 | 28.3 | 6000 | 0.3056 | 0.3880 |
| 1.0366 | 33.02 | 7000 | 0.2997 | 0.3665 |
| 0.9988 | 37.74 | 8000 | 0.2972 | 0.3653 |
| 0.9864 | 42.45 | 9000 | 0.2697 | 0.3371 |
| 0.9558 | 47.17 | 10000 | 0.2739 | 0.3141 |
| 0.9094 | 51.89 | 11000 | 0.2657 | 0.3533 |
| 0.9034 | 56.6 | 12000 | 0.2699 | 0.3397 |
| 0.8907 | 61.32 | 13000 | 0.2765 | 0.3470 |
| 0.8631 | 66.04 | 14000 | 0.2774 | 0.3346 |
| 0.8389 | 70.75 | 15000 | 0.2743 | 0.3365 |
| 0.8214 | 75.47 | 16000 | 0.2778 | 0.3201 |
| 0.8195 | 80.19 | 17000 | 0.2725 | 0.3286 |
| 0.7994 | 84.91 | 18000 | 0.2782 | 0.3315 |
| 0.7816 | 89.62 | 19000 | 0.2775 | 0.3363 |
| 0.7816 | 94.34 | 20000 | 0.2731 | 0.3278 |
| 0.7635 | 99.06 | 21000 | 0.2767 | 0.3259 |