Instructions to use Salama1429/tarteel-ai-whisper-base-ar-quran with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salama1429/tarteel-ai-whisper-base-ar-quran with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Salama1429/tarteel-ai-whisper-base-ar-quran")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Salama1429/tarteel-ai-whisper-base-ar-quran") model = AutoModelForSpeechSeq2Seq.from_pretrained("Salama1429/tarteel-ai-whisper-base-ar-quran", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
eee1eef
1
Parent(s): 6826460
Upload processor
Browse files- preprocessor_config.json +0 -0
- tokenizer_config.json +3 -3
preprocessor_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -18,13 +19,12 @@
|
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
-
"model_max_length":
|
| 22 |
-
"name_or_path": "openai/whisper-base",
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
| 26 |
-
"special_tokens_map_file": null,
|
| 27 |
"tokenizer_class": "WhisperTokenizer",
|
|
|
|
| 28 |
"unk_token": {
|
| 29 |
"__type": "AddedToken",
|
| 30 |
"content": "",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
+
"model_max_length": 1024,
|
|
|
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 26 |
"tokenizer_class": "WhisperTokenizer",
|
| 27 |
+
"trust_remote_code": false,
|
| 28 |
"unk_token": {
|
| 29 |
"__type": "AddedToken",
|
| 30 |
"content": "",
|