Downloads · 30 days
7
18% of all-time downloads
HouraMor/wh-stage1ft-lr5e6-dtstf5-adm-ga1ba16-st15k-v2-evalstp50-pat20-trainvalch
wh-stage1ft-lr5e6-dtstf5-adm-ga1ba16-st15k-v2-evalstp50-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
7
18% of all-time downloads
All-time downloads
38
Public
Parameters
1.5B
204 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 openai/whisper-large-v3 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 |
|---|---|---|---|---|---|
| 3.4814 | 0.1004 | 50 | 3.3103 | 0.3240 | 0.2580 |
| 2.0318 | 0.2008 | 100 | 2.0770 | 0.3268 | 0.2614 |
| 1.3303 | 0.3012 | 150 | 1.0776 | 0.3313 | 0.2674 |
| 0.9736 | 0.4016 | 200 | 0.8519 | 0.3728 | 0.3006 |
| 0.8537 | 0.5020 | 250 | 0.8240 | 0.3799 | 0.3018 |
| 0.7978 | 0.6024 | 300 | 0.7979 | 0.3745 | 0.3038 |
| 1.0115 | 0.7028 | 350 | 0.7835 | 0.3992 | 0.3125 |
| 0.778 | 0.8032 | 400 | 0.7627 | 0.4109 | 0.3241 |
| 0.8242 | 0.9036 | 450 | 0.7413 | 0.4555 | 0.3786 |
| 0.8856 | 1.0040 | 500 | 0.7484 | 0.5049 | 0.3956 |
| 0.467 | 1.1044 | 550 | 0.7594 | 0.4278 | 0.3317 |
| 0.3967 | 1.2048 | 600 | 0.7531 | 0.3253 | 0.2433 |
| 0.6078 | 1.3052 | 650 | 0.7594 | 0.3498 | 0.2827 |
| 0.6106 | 1.4056 | 700 | 0.7407 | 0.3759 | 0.3034 |
| 0.5975 | 1.5060 | 750 | 0.7332 | 0.3998 | 0.3156 |
| 0.5283 | 1.6064 | 800 | 0.7479 | 0.3874 | 0.3032 |
| 0.5951 | 1.7068 | 850 | 0.7274 | 0.3091 | 0.2382 |
| 0.5058 | 1.8072 | 900 | 0.7226 | 0.3137 | 0.2383 |
| 0.7103 | 1.9076 | 950 | 0.7228 | 0.4061 | 0.3209 |
| 0.3138 | 2.0080 | 1000 | 0.7169 | 0.4110 | 0.3328 |
| 0.4268 | 2.1084 | 1050 | 0.7567 | 0.3220 | 0.2653 |
| 0.4342 | 2.2088 | 1100 | 0.7706 | 0.2965 | 0.2318 |
| 0.3187 | 2.3092 | 1150 | 0.7655 | 0.3132 | 0.2469 |
| 0.3655 | 2.4096 | 1200 | 0.7648 | 0.3292 | 0.2616 |
| 0.2656 | 2.5100 | 1250 | 0.7690 | 0.2889 | 0.2199 |
| 0.3078 | 2.6104 | 1300 | 0.7642 | 0.3503 | 0.2705 |
| 0.303 | 2.7108 | 1350 | 0.7553 | 0.3109 | 0.2416 |
| 0.314 | 2.8112 | 1400 | 0.7567 | 0.3333 | 0.2550 |
| 0.3863 | 2.9116 | 1450 | 0.7658 | 0.3112 | 0.2377 |
| 0.144 | 3.0120 | 1500 | 0.7826 | 0.3034 | 0.2322 |
| 0.1673 | 3.1124 | 1550 | 0.8486 | 0.3052 | 0.2311 |
| 0.2207 | 3.2129 | 1600 | 0.8259 | 0.3238 | 0.2451 |
| 0.118 | 3.3133 | 1650 | 0.8756 | 0.3284 | 0.2794 |
| 0.1069 | 3.4137 | 1700 | 0.8645 | 0.3033 | 0.2273 |
| 0.2024 | 3.5141 | 1750 | 0.8295 | 0.3625 | 0.2966 |