Instructions to use addy88/hindi-wav2vec2-stt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use addy88/hindi-wav2vec2-stt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="addy88/hindi-wav2vec2-stt")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("addy88/hindi-wav2vec2-stt") model = AutoModelForCTC.from_pretrained("addy88/hindi-wav2vec2-stt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Create special_tokens_map.json
Browse files- special_tokens_map.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|