Instructions to use KBLab/kb-whisper-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KBLab/kb-whisper-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="KBLab/kb-whisper-small")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("KBLab/kb-whisper-small") model = AutoModelForSpeechSeq2Seq.from_pretrained("KBLab/kb-whisper-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload fixed & optimized fp16/q4f16 ONNX weights (#1)
Browse files- Upload fixed & optimized fp16/q4f16 ONNX weights (424a798f855410695ece7652ce686600d4149724)
Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>
onnx/decoder_model_merged_fp16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a46ed110545acf0c76b81162abf04ccb59994a1a999a792fb3e4a1560b8ee06e
|
| 3 |
+
size 308072830
|
onnx/decoder_model_merged_q4f16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a863f00364adb1ac6c77f5751c6a47fcdd16944bf6743813693b13aead43b70e
|
| 3 |
+
size 145279679
|