whisper-large-v3-eole / config.json
davidmeikle's picture
Upload folder using huggingface_hub
4121084 verified
{
"save_data": null,
"share_vocab": true,
"tgt_vocab_size": 51866,
"n_sample": 0,
"decoder_start_token": "<|startoftranscript|>",
"tgt_vocab": null,
"pad_token": "<|endoftext|>",
"skip_empty_level": "silent",
"bos_token": "<|endoftext|>",
"src_vocab_size": 51866,
"vocab_size_multiple": 8,
"data": null,
"src_vocab": null,
"eos_token": "<|endoftext|>",
"transforms": [
"huggingface_tokenize"
],
"unk_token": "<|endoftext|>",
"training": {
"quant_type": "",
"compute_dtype": "torch.float16",
"w_bit": 0,
"batch_size": 896,
"normalization": "tokens",
"accum_count": [
32
],
"batch_type": "tokens",
"group_size": 0,
"batch_size_multiple": 1,
"accum_steps": [
0
],
"quant_layers": [],
"valid_batch_size": 256
},
"model": {
"heads_kv": 20,
"add_qkvbias": true,
"left_pad": false,
"attn_scaling": null,
"transformer_ff": 5120,
"heads": 20,
"first_k_dense_replace": 0,
"generator_bias": false,
"position_encoding_type": "Learned",
"no_timestamps_token_id": 50364,
"mlp_activation_fn": "gelu",
"sliding_window": 4096,
"layers": 32,
"huggingface_model": "openai/whisper-large-v3",
"architecture": "whisper",
"norm_eps": 1e-05,
"moe_transformer_ff": null,
"num_experts_per_tok": 0,
"layer_norm": "standard",
"num_shared_experts": 0,
"begin_suppress_tokens": [
220,
50257
],
"shared_layer_norm": 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,
50359,
50360,
50361,
50362,
50363
],
"head_dim": null,
"hidden_size": 1280,
"share_decoder_embeddings": true,
"adapter_bias": false,
"word_timestamp_heads": [
[
7,
0
],
[
10,
17
],
[
12,
18
],
[
13,
12
],
[
16,
1
],
[
17,
14
],
[
19,
11
],
[
21,
4
],
[
24,
1
],
[
25,
6
]
],
"add_ffnbias": true,
"add_key_bias": false,
"parallel_residual": false,
"num_experts": 0,
"add_final_linear_bias": true,
"decoder": {
"heads_kv": 20,
"decoder_type": "transformer",
"layer_norm": "standard",
"num_shared_experts": 0,
"add_qkvbias": true,
"attn_scaling": null,
"shared_layer_norm": false,
"tgt_word_vec_size": 1280,
"transformer_ff": 5120,
"first_k_dense_replace": 0,
"heads": 20,
"head_dim": null,
"hidden_size": 1280,
"position_encoding_type": "Learned",
"mlp_activation_fn": "gelu",
"add_ffnbias": true,
"sliding_window": 4096,
"layers": 32,
"add_key_bias": false,
"n_positions": 448,
"norm_eps": 1e-05,
"parallel_residual": false,
"num_experts": 0,
"moe_transformer_ff": null,
"add_final_linear_bias": true,
"num_experts_per_tok": 0
},
"embeddings": {
"src_word_vec_size": 1280,
"position_encoding_type": "Learned",
"tgt_word_vec_size": 1280,
"n_positions": 448
},
"encoder": {
"heads_kv": 20,
"src_word_vec_size": 1280,
"layer_norm": "standard",
"num_shared_experts": 0,
"add_qkvbias": true,
"encoder_type": "whisper",
"attn_scaling": null,
"shared_layer_norm": false,
"transformer_ff": 5120,
"heads": 20,
"first_k_dense_replace": 0,
"head_dim": null,
"hidden_size": 1280,
"position_encoding_type": null,
"num_mel_bins": 128,
"mlp_activation_fn": "gelu",
"add_ffnbias": true,
"sliding_window": 4096,
"layers": 32,
"add_key_bias": false,
"norm_eps": 1e-05,
"parallel_residual": false,
"num_experts": 0,
"moe_transformer_ff": null,
"max_source_positions": 1500,
"add_final_linear_bias": true,
"num_experts_per_tok": 0
}
},
"transforms_configs": {
"huggingface_tokenize": {
"path": "/scratch/models/whisper-large-v3-eole/tokenizer.json",
"huggingface_model": "openai/whisper-large-v3"
}
},
"inference": {
"optional_eos": [],
"max_length": 448,
"chat_template": null
}
}