Instructions to use GroupSix/whisper-small-sv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GroupSix/whisper-small-sv with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="GroupSix/whisper-small-sv")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("GroupSix/whisper-small-sv") model = AutoModelForSpeechSeq2Seq.from_pretrained("GroupSix/whisper-small-sv", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Manual commit
Browse files- README.md +1 -1
- preprocessor_config.json +14 -0
- training_args.bin +0 -0
README.md
CHANGED
|
@@ -60,4 +60,4 @@ The following hyperparameters were used during training:
|
|
| 60 |
- Transformers 4.36.0.dev0
|
| 61 |
- Pytorch 2.1.0+cu118
|
| 62 |
- Datasets 2.15.0
|
| 63 |
-
- Tokenizers 0.15.0
|
|
|
|
| 60 |
- Transformers 4.36.0.dev0
|
| 61 |
- Pytorch 2.1.0+cu118
|
| 62 |
- Datasets 2.15.0
|
| 63 |
+
- Tokenizers 0.15.0
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
+
"feature_size": 80,
|
| 5 |
+
"hop_length": 160,
|
| 6 |
+
"n_fft": 400,
|
| 7 |
+
"n_samples": 480000,
|
| 8 |
+
"nb_max_frames": 3000,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"padding_value": 0.0,
|
| 11 |
+
"processor_class": "WhisperProcessor",
|
| 12 |
+
"return_attention_mask": false,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|
training_args.bin
ADDED
|
Binary file (4.92 kB). View file
|
|
|