Instructions to use Korla/whisper_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Korla/whisper_test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Korla/whisper_test")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Korla/whisper_test") model = AutoModel.from_pretrained("Korla/whisper_test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"activation_function": "gelu",
|
| 4 |
"apply_spec_augment": false,
|
| 5 |
"architectures": [
|
| 6 |
-
"
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"begin_suppress_tokens": [
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
"num_mel_bins": 128,
|
| 42 |
"pad_token_id": 50257,
|
| 43 |
"scale_embedding": false,
|
| 44 |
-
"torch_dtype": "
|
| 45 |
"transformers_version": "4.51.3",
|
| 46 |
"use_cache": true,
|
| 47 |
"use_weighted_layer_sum": false,
|
|
|
|
| 3 |
"activation_function": "gelu",
|
| 4 |
"apply_spec_augment": false,
|
| 5 |
"architectures": [
|
| 6 |
+
"WhisperModel"
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"begin_suppress_tokens": [
|
|
|
|
| 41 |
"num_mel_bins": 128,
|
| 42 |
"pad_token_id": 50257,
|
| 43 |
"scale_embedding": false,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
"transformers_version": "4.51.3",
|
| 46 |
"use_cache": true,
|
| 47 |
"use_weighted_layer_sum": false,
|
model.safetensors
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 sha256:703d1ac9099bbf6907ffab80158f79f7bb02b63a1ec60b2a4418cf0e6b5f7a91
|
| 3 |
+
size 3235577888
|