kijai
38fd791a77
commit fda0fe6e0c21eb10276ae302cd88b6cbcf5b36b5 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 16:55:00 2025 +0300 Create wanvideo_HuMo_example_01.json commit cffe3039c3d2fbacd4803329bf31b5fdc45215ba Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 16:30:49 2025 +0300 Update model.py commit ddce018a5a6ffeb926860342889b12efb7343ec0 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 16:29:27 2025 +0300 cleanup commit 8c021b8b3f66144804e500e74aa6f2be52f9f9fc Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 16:23:27 2025 +0300 avoid compile graph break commit ef9c7732042261581b4bba6d980def78633f56dc Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 16:16:13 2025 +0300 Allow using whisper model without decoder layers commit 8d0ba29ee84d14be6084ecbcee1cbc9414128fb3 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 15:55:26 2025 +0300 start/end percent for HuMo audio commit bfe0d358a8820240f262351e61cfb979cb9a47ff Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 15:37:11 2025 +0300 cleanup commit e563ae317f24a7f5751b43cdef4bffbaeaea5114 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Sat Sep 13 14:02:21 2025 +0300 Make audio work commit 95855196c51b1124a19079b746c5d12ec70d9026 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Fri Sep 12 18:10:04 2025 +0300 cfg commit d5a18b090fe719b7f0b00a0f68e6824685598313 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Fri Sep 12 03:10:15 2025 +0300 wrong way around commit 34c8c4842c14002fe4694dfa23c24a65b7ea39d0 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Fri Sep 12 03:01:45 2025 +0300 Update nodes.py commit 47d1e2ab5f3e1483782d0739f5b51cdd33707c36 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Fri Sep 12 02:47:03 2025 +0300 update image inputs are working but audio still doesn't do anything commit 67890d816a64459944091cb01478c1e0ec4c4a82 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Thu Sep 11 21:13:12 2025 +0300 update commit dbcef53405bb78feae4c5d2c6b310b76e4ef9949 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Thu Sep 11 17:09:37 2025 +0300 Update model.py commit 92c9aac51f4d37988757510a4e57179834cc5de2 Author: kijai <40791699+kijai@users.noreply.github.com> Date: Thu Sep 11 16:15:39 2025 +0300 init untested as no weights released as of yet
51 lines
1.2 KiB
JSON
51 lines
1.2 KiB
JSON
{
|
|
"_name_or_path": "openai/whisper-large-v3",
|
|
"activation_dropout": 0.0,
|
|
"activation_function": "gelu",
|
|
"apply_spec_augment": false,
|
|
"architectures": [
|
|
"WhisperForConditionalGeneration"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"begin_suppress_tokens": [
|
|
220,
|
|
50257
|
|
],
|
|
"bos_token_id": 50257,
|
|
"classifier_proj_size": 256,
|
|
"d_model": 1280,
|
|
"decoder_attention_heads": 20,
|
|
"decoder_ffn_dim": 5120,
|
|
"decoder_layerdrop": 0.0,
|
|
"decoder_layers": 32,
|
|
"decoder_start_token_id": 50258,
|
|
"dropout": 0.0,
|
|
"encoder_attention_heads": 20,
|
|
"encoder_ffn_dim": 5120,
|
|
"encoder_layerdrop": 0.0,
|
|
"encoder_layers": 32,
|
|
"eos_token_id": 50257,
|
|
"init_std": 0.02,
|
|
"is_encoder_decoder": true,
|
|
"mask_feature_length": 10,
|
|
"mask_feature_min_masks": 0,
|
|
"mask_feature_prob": 0.0,
|
|
"mask_time_length": 10,
|
|
"mask_time_min_masks": 2,
|
|
"mask_time_prob": 0.05,
|
|
"max_length": 448,
|
|
"max_source_positions": 1500,
|
|
"max_target_positions": 448,
|
|
"median_filter_width": 7,
|
|
"model_type": "whisper",
|
|
"num_hidden_layers": 32,
|
|
"num_mel_bins": 128,
|
|
"pad_token_id": 50256,
|
|
"scale_embedding": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.36.0.dev0",
|
|
"use_cache": true,
|
|
"use_weighted_layer_sum": false,
|
|
"vocab_size": 51866
|
|
}
|