Automatic Speech Recognition
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results (legacy)
Instructions to use kksukk/hubert_zeroth_gpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kksukk/hubert_zeroth_gpu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kksukk/hubert_zeroth_gpu")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("kksukk/hubert_zeroth_gpu") model = AutoModelForCTC.from_pretrained("kksukk/hubert_zeroth_gpu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +10 -0
- tokenizer_config.json +1 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"name_or_path": "./",
|
| 6 |
"pad_token": "[PAD]",
|
|
|
|
| 7 |
"replace_word_delimiter_char": " ",
|
| 8 |
"special_tokens_map_file": null,
|
| 9 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"name_or_path": "./",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
"special_tokens_map_file": null,
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|