Instructions to use onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external") model = AutoModelForSpeechSeq2Seq.from_pretrained("onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +11 -0
config.json
CHANGED
|
@@ -50,6 +50,17 @@
|
|
| 50 |
"scale_embedding": false,
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
"transformers_version": "4.48.3",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
"use_cache": true,
|
| 54 |
"use_weighted_layer_sum": false,
|
| 55 |
"vocab_size": 51864
|
|
|
|
| 50 |
"scale_embedding": false,
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
"transformers_version": "4.48.3",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": {
|
| 55 |
+
"encoder_model": "fp32",
|
| 56 |
+
"decoder_model_merged": "q4"
|
| 57 |
+
},
|
| 58 |
+
"use_external_data_format": {
|
| 59 |
+
"encoder_model.onnx": false,
|
| 60 |
+
"decoder_model_merged.onnx": 2,
|
| 61 |
+
"decoder_model_merged_q4.onnx": 2
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
"use_cache": true,
|
| 65 |
"use_weighted_layer_sum": false,
|
| 66 |
"vocab_size": 51864
|