GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
basha3la2
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
basha3la2
Model Tree
basha3la2/whisper-base-de-v2
Input Modalities
Output Modalities
Supported Functionality
This is the third round of fine-tuning Whisper Base for German ASR:
| Round | Base Model | Dataset | Steps | WER |
|---|---|---|---|---|
| v1 | openai/whisper-base | flozi00/common_voice_19_0_de-labeled | 4,000 | ~15.6% |
| v2 | basha3la2/whisper-base-de | flozi00/asr-german-mixed | 15,000 | 14.16% |
| v3 | basha3la2/whisper-base-de-v2 | flozi00/asr-german-mixed | ~10,000 | 13.05% |
Training for v3 was planned for 30,000 steps but was interrupted at approximately step 10,000 due to Kaggle's 12-hour session limit. The last checkpoint was saved and pushed to the Hub. Further training continues in v4.
| Training Loss | Step | Validation Loss | Wer |
|---|---|---|---|
| 0.8029 | 5000 | 0.2134 | 13.7950 |
| 0.7785 | 10000 | 0.2006 | 13.0467 |
German automatic speech recognition, deployed on Radxa Rock 5B+ via RKNN (NPU inference).