GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
xl-24
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
xl-24
Model Tree
openai/whisper-small.en
Input Modalities
Output Modalities
Supported Functionality
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5297 | 1.0 | 742 | 0.5092 | 21.4217 |
| 0.2772 | 2.0 | 1484 | 0.4669 | 19.0886 |
| 0.1496 | 3.0 | 2226 | 0.4692 | 20.2620 |
| 0.0745 | 4.0 | 2968 | 0.4898 | 22.7043 |
| 0.0296 | 5.0 | 3710 | 0.5202 | 18.4336 |
| 0.0161 | 6.0 | 4452 | 0.5168 | 17.9697 |
| 0.0158 | 7.0 | 5194 | 0.5591 | 20.9851 |
| 0.0076 | 8.0 | 5936 | 0.5519 | 18.4336 |
| 0.0099 | 9.0 | 6678 | 0.5689 | 18.2153 |
| 0.0059 | 10.0 | 7420 | 0.5904 | 18.5428 |