Instructions to use Byne/whisper-large-v3-arabic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Byne/whisper-large-v3-arabic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Byne/whisper-large-v3-arabic")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Byne/whisper-large-v3-arabic") model = AutoModelForSpeechSeq2Seq.from_pretrained("Byne/whisper-large-v3-arabic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +9 -5
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"activation_function": "gelu",
|
| 4 |
"apply_spec_augment": false,
|
|
@@ -6,7 +7,10 @@
|
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
-
"begin_suppress_tokens":
|
|
|
|
|
|
|
|
|
|
| 10 |
"bos_token_id": 50257,
|
| 11 |
"classifier_proj_size": 256,
|
| 12 |
"d_model": 1280,
|
|
@@ -15,7 +19,7 @@
|
|
| 15 |
"decoder_layerdrop": 0.0,
|
| 16 |
"decoder_layers": 32,
|
| 17 |
"decoder_start_token_id": 50258,
|
| 18 |
-
"dropout": 0.
|
| 19 |
"encoder_attention_heads": 20,
|
| 20 |
"encoder_ffn_dim": 5120,
|
| 21 |
"encoder_layerdrop": 0.0,
|
|
@@ -29,7 +33,7 @@
|
|
| 29 |
"mask_time_length": 10,
|
| 30 |
"mask_time_min_masks": 2,
|
| 31 |
"mask_time_prob": 0.05,
|
| 32 |
-
"max_length":
|
| 33 |
"max_source_positions": 1500,
|
| 34 |
"max_target_positions": 448,
|
| 35 |
"median_filter_width": 7,
|
|
@@ -38,8 +42,8 @@
|
|
| 38 |
"num_mel_bins": 128,
|
| 39 |
"pad_token_id": 50256,
|
| 40 |
"scale_embedding": false,
|
| 41 |
-
"torch_dtype": "
|
| 42 |
-
"transformers_version": "4.
|
| 43 |
"use_cache": true,
|
| 44 |
"use_weighted_layer_sum": false,
|
| 45 |
"vocab_size": 51866
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "openai/whisper-large-v3",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
|
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
+
"begin_suppress_tokens": [
|
| 11 |
+
220,
|
| 12 |
+
50257
|
| 13 |
+
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
"classifier_proj_size": 256,
|
| 16 |
"d_model": 1280,
|
|
|
|
| 19 |
"decoder_layerdrop": 0.0,
|
| 20 |
"decoder_layers": 32,
|
| 21 |
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
"encoder_attention_heads": 20,
|
| 24 |
"encoder_ffn_dim": 5120,
|
| 25 |
"encoder_layerdrop": 0.0,
|
|
|
|
| 33 |
"mask_time_length": 10,
|
| 34 |
"mask_time_min_masks": 2,
|
| 35 |
"mask_time_prob": 0.05,
|
| 36 |
+
"max_length": 448,
|
| 37 |
"max_source_positions": 1500,
|
| 38 |
"max_target_positions": 448,
|
| 39 |
"median_filter_width": 7,
|
|
|
|
| 42 |
"num_mel_bins": 128,
|
| 43 |
"pad_token_id": 50256,
|
| 44 |
"scale_embedding": false,
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"transformers_version": "4.40.2",
|
| 47 |
"use_cache": true,
|
| 48 |
"use_weighted_layer_sum": false,
|
| 49 |
"vocab_size": 51866
|