Automatic Speech Recognition
Transformers
Safetensors
Hindi
whisper
speech-recognition
hindi
hinglish
Instructions to use MmeOG/MME_STT_Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MmeOG/MME_STT_Model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MmeOG/MME_STT_Model")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("MmeOG/MME_STT_Model") model = AutoModelForSpeechSeq2Seq.from_pretrained("MmeOG/MME_STT_Model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|endoftext|>",
|
| 7 |
"errors": "replace",
|
| 8 |
-
"
|
| 9 |
"<|startoftranscript|>",
|
| 10 |
"<|en|>",
|
| 11 |
"<|zh|>",
|
|
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|endoftext|>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"additional_special_tokens": [
|
| 9 |
"<|startoftranscript|>",
|
| 10 |
"<|en|>",
|
| 11 |
"<|zh|>",
|