Instructions to use scribe-project/wav2vec2-large-voxrex-300m-radio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use scribe-project/wav2vec2-large-voxrex-300m-radio with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="scribe-project/wav2vec2-large-voxrex-300m-radio")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("scribe-project/wav2vec2-large-voxrex-300m-radio") model = AutoModelForCTC.from_pretrained("scribe-project/wav2vec2-large-voxrex-300m-radio", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
7413c08
1
Parent(s): cf5a322
Upload processor
Browse files- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
|
@@ -5,6 +5,7 @@
|
|
| 5 |
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
"name_or_path": "./",
|
| 7 |
"pad_token": "[PAD]",
|
|
|
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
"special_tokens_map_file": null,
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 5 |
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
"name_or_path": "./",
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
+
"processor_class": "Wav2Vec2Processor",
|
| 9 |
"replace_word_delimiter_char": " ",
|
| 10 |
"special_tokens_map_file": null,
|
| 11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|