Instructions to use TriLinSL/whisper-medium-si-ta-en-split1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TriLinSL/whisper-medium-si-ta-en-split1 with PEFT:
Task type is invalid.
- Transformers
How to use TriLinSL/whisper-medium-si-ta-en-split1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TriLinSL/whisper-medium-si-ta-en-split1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
best adapter: step 3000, val WER 24.99
Browse files
best_adapter/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 138520208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8e18a4d46e1c2721928bfd6bbefd42d6ad4180e0eec27f52d96748253e0790
|
| 3 |
size 138520208
|
best_adapter/best_metrics.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"step":
|
|
|
|
| 1 |
+
{"step": 3000, "eval_wer": 24.989939023417747, "eval_cer": 6.623053518269356}
|