Upload WhisperForConditionalGeneration
#93
by
denzim
- opened
- config.json +11 -1
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
"_name_or_path": "openai/whisper-large-v2",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
|
|
| 5 |
"architectures": [
|
| 6 |
"WhisperForConditionalGeneration"
|
| 7 |
],
|
|
@@ -11,6 +12,7 @@
|
|
| 11 |
50257
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
|
|
|
| 14 |
"d_model": 1280,
|
| 15 |
"decoder_attention_heads": 20,
|
| 16 |
"decoder_ffn_dim": 5120,
|
|
@@ -39,9 +41,16 @@
|
|
| 39 |
],
|
| 40 |
"init_std": 0.02,
|
| 41 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"max_length": 448,
|
| 43 |
"max_source_positions": 1500,
|
| 44 |
"max_target_positions": 448,
|
|
|
|
| 45 |
"model_type": "whisper",
|
| 46 |
"num_hidden_layers": 32,
|
| 47 |
"num_mel_bins": 80,
|
|
@@ -138,7 +147,8 @@
|
|
| 138 |
50362
|
| 139 |
],
|
| 140 |
"torch_dtype": "float32",
|
| 141 |
-
"transformers_version": "4.
|
| 142 |
"use_cache": true,
|
|
|
|
| 143 |
"vocab_size": 51865
|
| 144 |
}
|
|
|
|
| 2 |
"_name_or_path": "openai/whisper-large-v2",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
"architectures": [
|
| 7 |
"WhisperForConditionalGeneration"
|
| 8 |
],
|
|
|
|
| 12 |
50257
|
| 13 |
],
|
| 14 |
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
"d_model": 1280,
|
| 17 |
"decoder_attention_heads": 20,
|
| 18 |
"decoder_ffn_dim": 5120,
|
|
|
|
| 41 |
],
|
| 42 |
"init_std": 0.02,
|
| 43 |
"is_encoder_decoder": true,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.0,
|
| 47 |
+
"mask_time_length": 10,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.05,
|
| 50 |
"max_length": 448,
|
| 51 |
"max_source_positions": 1500,
|
| 52 |
"max_target_positions": 448,
|
| 53 |
+
"median_filter_width": 7,
|
| 54 |
"model_type": "whisper",
|
| 55 |
"num_hidden_layers": 32,
|
| 56 |
"num_mel_bins": 80,
|
|
|
|
| 147 |
50362
|
| 148 |
],
|
| 149 |
"torch_dtype": "float32",
|
| 150 |
+
"transformers_version": "4.36.2",
|
| 151 |
"use_cache": true,
|
| 152 |
+
"use_weighted_layer_sum": false,
|
| 153 |
"vocab_size": 51865
|
| 154 |
}
|
generation_config.json
CHANGED
|
@@ -311,5 +311,5 @@
|
|
| 311 |
"transcribe": 50359,
|
| 312 |
"translate": 50358
|
| 313 |
},
|
| 314 |
-
"transformers_version": "4.
|
| 315 |
}
|
|
|
|
| 311 |
"transcribe": 50359,
|
| 312 |
"translate": 50358
|
| 313 |
},
|
| 314 |
+
"transformers_version": "4.36.2"
|
| 315 |
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a9fc8ea3fb1810298d1ed34154ff295867d0a54570f38573c470bfdcf231a9
|
| 3 |
+
size 4992706480
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c6c46b5bb35b8b60b7bf75a388b3a8a5387c935e907990c5608359da0c4c69c
|
| 3 |
+
size 1180663192
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|