Instructions to use seba3y/whisper-tiny-fluency with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seba3y/whisper-tiny-fluency with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="seba3y/whisper-tiny-fluency")# Load model directly from transformers import AutoProcessor, AutoModelForAudioClassification processor = AutoProcessor.from_pretrained("seba3y/whisper-tiny-fluency") model = AutoModelForAudioClassification.from_pretrained("seba3y/whisper-tiny-fluency", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload WhisperForAudioClassification
Browse files- config.json +2 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
@@ -67,6 +67,7 @@
|
|
| 67 |
"num_hidden_layers": 4,
|
| 68 |
"num_mel_bins": 80,
|
| 69 |
"pad_token_id": 50257,
|
|
|
|
| 70 |
"scale_embedding": false,
|
| 71 |
"suppress_tokens": [
|
| 72 |
1,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "audio_sent_fluency/checkpoint-1180",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
|
|
| 67 |
"num_hidden_layers": 4,
|
| 68 |
"num_mel_bins": 80,
|
| 69 |
"pad_token_id": 50257,
|
| 70 |
+
"return_dict": false,
|
| 71 |
"scale_embedding": false,
|
| 72 |
"suppress_tokens": [
|
| 73 |
1,
|