Downloads · 30 days
4
16% of all-time downloads
HouraMor/wh-ft-lr5e5-dtstf5-adm-ga1ba16-st15k-v2-evalstp10-pat20-trainvalch
wh-ft-lr5e5-dtstf5-adm-ga1ba16-st15k-v2-evalstp10-pat20-trainvalch is a automatic speech recognition model from HouraMor. 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
4
16% of all-time downloads
All-time downloads
25
Public
Parameters
1.5B
98.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of HouraMor/wh-ft-lr5e6-dtstf5-adm-ga1ba16-st15k-v2-evalstp500-pat5 on an unknown 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 | Cer |
|---|---|---|---|---|---|
| 0.3621 | 0.0201 | 10 | 0.5632 | 0.2973 | 0.2250 |
| 0.2967 | 0.0402 | 20 | 0.5648 | 0.2770 | 0.2080 |
| 0.194 | 0.0602 | 30 | 0.5726 | 0.2765 | 0.2079 |
| 0.3778 | 0.0803 | 40 | 0.5808 | 0.2779 | 0.2089 |
| 0.2958 | 0.1004 | 50 | 0.5975 | 0.2923 | 0.2234 |
| 0.3074 | 0.1205 | 60 | 0.6034 | 0.3001 | 0.2279 |
| 0.2909 | 0.1406 | 70 | 0.6213 | 0.3212 | 0.2373 |
| 0.3392 | 0.1606 | 80 | 0.6431 | 0.3036 | 0.2246 |
| 0.3746 | 0.1807 | 90 | 0.6439 | 0.3394 | 0.2534 |
| 0.4158 | 0.2008 | 100 | 0.6532 | 0.3328 | 0.2610 |
| 0.4082 | 0.2209 | 110 | 0.6464 | 0.4084 | 0.3213 |
| 0.3412 | 0.2410 | 120 | 0.6943 | 0.4131 | 0.3093 |
| 0.4342 | 0.2610 | 130 | 0.6983 | 0.5884 | 0.4641 |
| 0.4548 | 0.2811 | 140 | 0.7045 | 0.4002 | 0.3012 |
| 0.6116 | 0.3012 | 150 | 0.6984 | 0.3547 | 0.2776 |
| 0.6484 | 0.3213 | 160 | 0.7095 | 0.3705 | 0.2725 |