Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- decoder/build.json +195 -0
- decoder/config.json +1 -0
- decoder/timings.cache +0 -0
- decoder/whisper_float16_tp1_rank0.engine +3 -0
- encoder/build.json +189 -0
- encoder/config.json +1 -0
- encoder/timings.cache +0 -0
- encoder/whisper_float16_tp1_rank0.engine +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
decoder/whisper_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
|
37 |
+
encoder/whisper_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
|
decoder/build.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"builder_config": {
|
3 |
+
"apply_query_key_layer_scaling": false,
|
4 |
+
"cross_attention": true,
|
5 |
+
"fp8": false,
|
6 |
+
"has_position_embedding": true,
|
7 |
+
"has_token_type_embedding": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 768,
|
10 |
+
"huggingface": {
|
11 |
+
"_name_or_path": "openai/whisper-small",
|
12 |
+
"activation_dropout": 0.0,
|
13 |
+
"activation_function": "gelu",
|
14 |
+
"architectures": [
|
15 |
+
"WhisperForConditionalGeneration"
|
16 |
+
],
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"begin_suppress_tokens": [
|
19 |
+
220,
|
20 |
+
50257
|
21 |
+
],
|
22 |
+
"bos_token_id": 50257,
|
23 |
+
"d_model": 768,
|
24 |
+
"decoder_attention_heads": 12,
|
25 |
+
"decoder_ffn_dim": 3072,
|
26 |
+
"decoder_layerdrop": 0.0,
|
27 |
+
"decoder_layers": 12,
|
28 |
+
"decoder_start_token_id": 50258,
|
29 |
+
"dropout": 0.0,
|
30 |
+
"encoder_attention_heads": 12,
|
31 |
+
"encoder_ffn_dim": 3072,
|
32 |
+
"encoder_layerdrop": 0.0,
|
33 |
+
"encoder_layers": 12,
|
34 |
+
"eos_token_id": 50257,
|
35 |
+
"forced_decoder_ids": [
|
36 |
+
[
|
37 |
+
1,
|
38 |
+
50259
|
39 |
+
],
|
40 |
+
[
|
41 |
+
2,
|
42 |
+
50359
|
43 |
+
],
|
44 |
+
[
|
45 |
+
3,
|
46 |
+
50363
|
47 |
+
]
|
48 |
+
],
|
49 |
+
"hidden_size": 768,
|
50 |
+
"init_std": 0.02,
|
51 |
+
"is_encoder_decoder": true,
|
52 |
+
"max_length": 448,
|
53 |
+
"max_sequence_length": 448,
|
54 |
+
"max_source_positions": 1500,
|
55 |
+
"max_target_positions": 448,
|
56 |
+
"model_type": "whisper",
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"num_layers": 12,
|
59 |
+
"num_mel_bins": 80,
|
60 |
+
"pad_token_id": 50257,
|
61 |
+
"scale_embedding": false,
|
62 |
+
"suppress_tokens": [
|
63 |
+
1,
|
64 |
+
2,
|
65 |
+
7,
|
66 |
+
8,
|
67 |
+
9,
|
68 |
+
10,
|
69 |
+
14,
|
70 |
+
25,
|
71 |
+
26,
|
72 |
+
27,
|
73 |
+
28,
|
74 |
+
29,
|
75 |
+
31,
|
76 |
+
58,
|
77 |
+
59,
|
78 |
+
60,
|
79 |
+
61,
|
80 |
+
62,
|
81 |
+
63,
|
82 |
+
90,
|
83 |
+
91,
|
84 |
+
92,
|
85 |
+
93,
|
86 |
+
359,
|
87 |
+
503,
|
88 |
+
522,
|
89 |
+
542,
|
90 |
+
873,
|
91 |
+
893,
|
92 |
+
902,
|
93 |
+
918,
|
94 |
+
922,
|
95 |
+
931,
|
96 |
+
1350,
|
97 |
+
1853,
|
98 |
+
1982,
|
99 |
+
2460,
|
100 |
+
2627,
|
101 |
+
3246,
|
102 |
+
3253,
|
103 |
+
3268,
|
104 |
+
3536,
|
105 |
+
3846,
|
106 |
+
3961,
|
107 |
+
4183,
|
108 |
+
4667,
|
109 |
+
6585,
|
110 |
+
6647,
|
111 |
+
7273,
|
112 |
+
9061,
|
113 |
+
9383,
|
114 |
+
10428,
|
115 |
+
10929,
|
116 |
+
11938,
|
117 |
+
12033,
|
118 |
+
12331,
|
119 |
+
12562,
|
120 |
+
13793,
|
121 |
+
14157,
|
122 |
+
14635,
|
123 |
+
15265,
|
124 |
+
15618,
|
125 |
+
16553,
|
126 |
+
16604,
|
127 |
+
18362,
|
128 |
+
18956,
|
129 |
+
20075,
|
130 |
+
21675,
|
131 |
+
22520,
|
132 |
+
26130,
|
133 |
+
26161,
|
134 |
+
26435,
|
135 |
+
28279,
|
136 |
+
29464,
|
137 |
+
31650,
|
138 |
+
32302,
|
139 |
+
32470,
|
140 |
+
36865,
|
141 |
+
42863,
|
142 |
+
47425,
|
143 |
+
49870,
|
144 |
+
50254,
|
145 |
+
50258,
|
146 |
+
50360,
|
147 |
+
50361,
|
148 |
+
50362
|
149 |
+
],
|
150 |
+
"torch_dtype": "float32",
|
151 |
+
"transformers_version": "4.27.0.dev0",
|
152 |
+
"use_cache": true,
|
153 |
+
"vocab_size": 51865
|
154 |
+
},
|
155 |
+
"int8": false,
|
156 |
+
"max_batch_size": 1,
|
157 |
+
"max_input_len": 1,
|
158 |
+
"max_output_len": 448,
|
159 |
+
"max_position_embeddings": 448,
|
160 |
+
"name": "whisper",
|
161 |
+
"num_heads": 12,
|
162 |
+
"num_layers": 12,
|
163 |
+
"precision": "float16",
|
164 |
+
"quant_mode": 0,
|
165 |
+
"tensor_parallel": 1,
|
166 |
+
"tensorrt": "9.2.0.post12.dev5",
|
167 |
+
"use_refit": false
|
168 |
+
},
|
169 |
+
"plugin_config": {
|
170 |
+
"attention_qk_half_accumulation": false,
|
171 |
+
"bert_attention_plugin": false,
|
172 |
+
"context_fmha_type": 1,
|
173 |
+
"gemm_plugin": "float16",
|
174 |
+
"gpt_attention_plugin": "float16",
|
175 |
+
"identity_plugin": false,
|
176 |
+
"layernorm_plugin": false,
|
177 |
+
"layernorm_quantization_plugin": false,
|
178 |
+
"lookup_plugin": false,
|
179 |
+
"lora_plugin": false,
|
180 |
+
"multi_block_mode": false,
|
181 |
+
"nccl_plugin": false,
|
182 |
+
"paged_kv_cache": false,
|
183 |
+
"quantize_per_token_plugin": false,
|
184 |
+
"quantize_tensor_plugin": false,
|
185 |
+
"remove_input_padding": true,
|
186 |
+
"rmsnorm_plugin": false,
|
187 |
+
"rmsnorm_quantization_plugin": false,
|
188 |
+
"smooth_quant_gemm_plugin": false,
|
189 |
+
"tokens_per_block": 0,
|
190 |
+
"use_custom_all_reduce": false,
|
191 |
+
"use_paged_context_fmha": false,
|
192 |
+
"weight_only_groupwise_quant_matmul_plugin": false,
|
193 |
+
"weight_only_quant_matmul_plugin": false
|
194 |
+
}
|
195 |
+
}
|
decoder/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_name_or_path": "openai/whisper-small", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": ["WhisperForConditionalGeneration"], "attention_dropout": 0.0, "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "d_model": 768, "decoder_attention_heads": 12, "decoder_ffn_dim": 3072, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 12, "encoder_ffn_dim": 3072, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 50257, "forced_decoder_ids": [[1, 50259], [2, 50359], [3, 50363]], "init_std": 0.02, "is_encoder_decoder": true, "max_length": 448, "max_source_positions": 1500, "max_target_positions": 448, "model_type": "whisper", "num_hidden_layers": 12, "num_mel_bins": 80, "pad_token_id": 50257, "scale_embedding": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50360, 50361, 50362], "torch_dtype": "float32", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 51865, "num_layers": 12, "max_sequence_length": 448, "hidden_size": 768}
|
decoder/timings.cache
ADDED
Binary file (102 kB). View file
|
|
decoder/whisper_float16_tp1_rank0.engine
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:932161932241b2e40711ecc96c46350a1d818ce2aac7572581d2eef407494c99
|
3 |
+
size 388396564
|
encoder/build.json
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"builder_config": {
|
3 |
+
"fp8": false,
|
4 |
+
"hidden_size": 768,
|
5 |
+
"huggingface": {
|
6 |
+
"_name_or_path": "openai/whisper-small",
|
7 |
+
"activation_dropout": 0.0,
|
8 |
+
"activation_function": "gelu",
|
9 |
+
"architectures": [
|
10 |
+
"WhisperForConditionalGeneration"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"begin_suppress_tokens": [
|
14 |
+
220,
|
15 |
+
50257
|
16 |
+
],
|
17 |
+
"bos_token_id": 50257,
|
18 |
+
"d_model": 768,
|
19 |
+
"decoder_attention_heads": 12,
|
20 |
+
"decoder_ffn_dim": 3072,
|
21 |
+
"decoder_layerdrop": 0.0,
|
22 |
+
"decoder_layers": 12,
|
23 |
+
"decoder_start_token_id": 50258,
|
24 |
+
"dropout": 0.0,
|
25 |
+
"encoder_attention_heads": 12,
|
26 |
+
"encoder_ffn_dim": 3072,
|
27 |
+
"encoder_layerdrop": 0.0,
|
28 |
+
"encoder_layers": 12,
|
29 |
+
"eos_token_id": 50257,
|
30 |
+
"forced_decoder_ids": [
|
31 |
+
[
|
32 |
+
1,
|
33 |
+
50259
|
34 |
+
],
|
35 |
+
[
|
36 |
+
2,
|
37 |
+
50359
|
38 |
+
],
|
39 |
+
[
|
40 |
+
3,
|
41 |
+
50363
|
42 |
+
]
|
43 |
+
],
|
44 |
+
"hidden_size": 768,
|
45 |
+
"init_std": 0.02,
|
46 |
+
"is_encoder_decoder": true,
|
47 |
+
"max_length": 448,
|
48 |
+
"max_sequence_length": 448,
|
49 |
+
"max_source_positions": 1500,
|
50 |
+
"max_target_positions": 448,
|
51 |
+
"model_type": "whisper",
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"num_layers": 12,
|
54 |
+
"num_mel_bins": 80,
|
55 |
+
"pad_token_id": 50257,
|
56 |
+
"scale_embedding": false,
|
57 |
+
"suppress_tokens": [
|
58 |
+
1,
|
59 |
+
2,
|
60 |
+
7,
|
61 |
+
8,
|
62 |
+
9,
|
63 |
+
10,
|
64 |
+
14,
|
65 |
+
25,
|
66 |
+
26,
|
67 |
+
27,
|
68 |
+
28,
|
69 |
+
29,
|
70 |
+
31,
|
71 |
+
58,
|
72 |
+
59,
|
73 |
+
60,
|
74 |
+
61,
|
75 |
+
62,
|
76 |
+
63,
|
77 |
+
90,
|
78 |
+
91,
|
79 |
+
92,
|
80 |
+
93,
|
81 |
+
359,
|
82 |
+
503,
|
83 |
+
522,
|
84 |
+
542,
|
85 |
+
873,
|
86 |
+
893,
|
87 |
+
902,
|
88 |
+
918,
|
89 |
+
922,
|
90 |
+
931,
|
91 |
+
1350,
|
92 |
+
1853,
|
93 |
+
1982,
|
94 |
+
2460,
|
95 |
+
2627,
|
96 |
+
3246,
|
97 |
+
3253,
|
98 |
+
3268,
|
99 |
+
3536,
|
100 |
+
3846,
|
101 |
+
3961,
|
102 |
+
4183,
|
103 |
+
4667,
|
104 |
+
6585,
|
105 |
+
6647,
|
106 |
+
7273,
|
107 |
+
9061,
|
108 |
+
9383,
|
109 |
+
10428,
|
110 |
+
10929,
|
111 |
+
11938,
|
112 |
+
12033,
|
113 |
+
12331,
|
114 |
+
12562,
|
115 |
+
13793,
|
116 |
+
14157,
|
117 |
+
14635,
|
118 |
+
15265,
|
119 |
+
15618,
|
120 |
+
16553,
|
121 |
+
16604,
|
122 |
+
18362,
|
123 |
+
18956,
|
124 |
+
20075,
|
125 |
+
21675,
|
126 |
+
22520,
|
127 |
+
26130,
|
128 |
+
26161,
|
129 |
+
26435,
|
130 |
+
28279,
|
131 |
+
29464,
|
132 |
+
31650,
|
133 |
+
32302,
|
134 |
+
32470,
|
135 |
+
36865,
|
136 |
+
42863,
|
137 |
+
47425,
|
138 |
+
49870,
|
139 |
+
50254,
|
140 |
+
50258,
|
141 |
+
50360,
|
142 |
+
50361,
|
143 |
+
50362
|
144 |
+
],
|
145 |
+
"torch_dtype": "float32",
|
146 |
+
"transformers_version": "4.27.0.dev0",
|
147 |
+
"use_cache": true,
|
148 |
+
"vocab_size": 51865
|
149 |
+
},
|
150 |
+
"int8": false,
|
151 |
+
"max_batch_size": 1,
|
152 |
+
"n_mels": 80,
|
153 |
+
"name": "whisper",
|
154 |
+
"num_heads": 12,
|
155 |
+
"num_languages": 99,
|
156 |
+
"num_layers": 12,
|
157 |
+
"precision": "float16",
|
158 |
+
"quant_mode": 0,
|
159 |
+
"tensor_parallel": 1,
|
160 |
+
"tensorrt": "9.2.0.post12.dev5",
|
161 |
+
"use_refit": false
|
162 |
+
},
|
163 |
+
"plugin_config": {
|
164 |
+
"attention_qk_half_accumulation": false,
|
165 |
+
"bert_attention_plugin": false,
|
166 |
+
"context_fmha_type": 1,
|
167 |
+
"gemm_plugin": "float16",
|
168 |
+
"gpt_attention_plugin": "float16",
|
169 |
+
"identity_plugin": false,
|
170 |
+
"layernorm_plugin": false,
|
171 |
+
"layernorm_quantization_plugin": false,
|
172 |
+
"lookup_plugin": false,
|
173 |
+
"lora_plugin": false,
|
174 |
+
"multi_block_mode": false,
|
175 |
+
"nccl_plugin": false,
|
176 |
+
"paged_kv_cache": false,
|
177 |
+
"quantize_per_token_plugin": false,
|
178 |
+
"quantize_tensor_plugin": false,
|
179 |
+
"remove_input_padding": true,
|
180 |
+
"rmsnorm_plugin": false,
|
181 |
+
"rmsnorm_quantization_plugin": false,
|
182 |
+
"smooth_quant_gemm_plugin": false,
|
183 |
+
"tokens_per_block": 0,
|
184 |
+
"use_custom_all_reduce": false,
|
185 |
+
"use_paged_context_fmha": false,
|
186 |
+
"weight_only_groupwise_quant_matmul_plugin": false,
|
187 |
+
"weight_only_quant_matmul_plugin": false
|
188 |
+
}
|
189 |
+
}
|
encoder/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_name_or_path": "openai/whisper-small", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": ["WhisperForConditionalGeneration"], "attention_dropout": 0.0, "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "d_model": 768, "decoder_attention_heads": 12, "decoder_ffn_dim": 3072, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 12, "encoder_ffn_dim": 3072, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 50257, "forced_decoder_ids": [[1, 50259], [2, 50359], [3, 50363]], "init_std": 0.02, "is_encoder_decoder": true, "max_length": 448, "max_source_positions": 1500, "max_target_positions": 448, "model_type": "whisper", "num_hidden_layers": 12, "num_mel_bins": 80, "pad_token_id": 50257, "scale_embedding": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50360, 50361, 50362], "torch_dtype": "float32", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 51865, "num_layers": 12, "max_sequence_length": 448, "hidden_size": 768}
|
encoder/timings.cache
ADDED
Binary file (217 kB). View file
|
|
encoder/whisper_float16_tp1_rank0.engine
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cec1582bb8aacee7c9005e0a3eb791de8c427825d64d927f4c0461aad071190a
|
3 |
+
size 183202884
|