Instructions to use JunWorks/Quantized_4bit_WhisperSmallStd_zhTW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JunWorks/Quantized_4bit_WhisperSmallStd_zhTW with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="JunWorks/Quantized_4bit_WhisperSmallStd_zhTW")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("JunWorks/Quantized_4bit_WhisperSmallStd_zhTW") model = AutoModelForSpeechSeq2Seq.from_pretrained("JunWorks/Quantized_4bit_WhisperSmallStd_zhTW") - Notebooks
- Google Colab
- Kaggle
Update generation_config.json
Browse filesremoved language = "mandarin", not really sure where that came from either
- generation_config.json +0 -1
generation_config.json
CHANGED
|
@@ -160,7 +160,6 @@
|
|
| 160 |
"<|yo|>": 50325,
|
| 161 |
"<|zh|>": 50260
|
| 162 |
},
|
| 163 |
-
"language": "mandarin",
|
| 164 |
"max_initial_timestamp_index": 50,
|
| 165 |
"max_length": 448,
|
| 166 |
"no_timestamps_token_id": 50363,
|
|
|
|
| 160 |
"<|yo|>": 50325,
|
| 161 |
"<|zh|>": 50260
|
| 162 |
},
|
|
|
|
| 163 |
"max_initial_timestamp_index": 50,
|
| 164 |
"max_length": 448,
|
| 165 |
"no_timestamps_token_id": 50363,
|