eaefc57d71
* 快速分类音频并把yml格式结果存在训练根目录里 (#190) * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update models.py * Update webui.py * Update infer.py * Create compress_model.py * 重新提交，更新Gradio推理UI (#193) * Update webui.py * Update webui.py * 更新 train_ms.py * 更新 models.py * 更新 models.py * 更新 models.py * 更新 train_ms.py * 更新 train_ms.py * 更新 models.py * Update preprocess_text.py * Update config.json * Update train_ms.py * Update webui.py (#206) * Add files via upload (#209) * Update train_ms.py * Update train_ms.py * Update preprocess_text.py * Update train_ms.py * fix (#211) * Update emotion_clustering.py * Add files via upload * Update emotion_clustering.py * add cluster center save * Add files via upload * Update config.py * Update default_config.yml * Update config.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update webui.py * Update emotion_clustering.py * Update commons.py * Update emotion_clustering.py * Update webui.py * Update webui.py * Add files via upload * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update webui.py * Update emotion_clustering.py * Update emotion_clustering.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix default_config.yml. * Update infer.py * feat: support infer 2.1 models * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: support infer 2.1 models 兼容bug修复 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py * Add CLAP * Fix data loader * Fix infer.py * Fix webui.py * Add prompt template * Update clap_gen.py * Fix wrong environ value * Add g for dur disc * Update clap_gen.py * Fix multilang generation * Update config.json * Prompt mode * Improve slice segments performance * Add preprocess webui * Update webui_preprocess.py * Update webui_preprocess.py * Update config.py * Update default_config.yml * Update config.py * Update clap_gen.py * Delete emo_gen.py * Delete get_emo.py * Delete emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim directory * Update README.md * Update README * Split val per lang * Delete emotion_clustering.py * Update default_config.yml * Update default_config.yml * Update config.py * Update preprocess_text.py * Update webui_preprocess.py * Update defalut_config.yml * Update webui_preprocess.py * Update preprocess_text.py * Random augmentation for CLAP * Update data_utils.py * Update preprocess_text.py * Add vq for CLAP features to avoid overfitting * Random dummy inputs * Update webui.py * Update models.py * Update infer.py * Apply Code Formatter Change * Update config.json * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: YYuX-1145 <138500330+YYuX-1145@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com>
208 lines
5.3 KiB
JSON
208 lines
5.3 KiB
JSON
{
|
|
"_commit_hash": null,
|
|
"architectures": [
|
|
"ClapModel"
|
|
],
|
|
"audio_config": {
|
|
"_name_or_path": "",
|
|
"add_cross_attention": false,
|
|
"aff_block_r": 4,
|
|
"architectures": null,
|
|
"attention_probs_dropout_prob": 0.0,
|
|
"bad_words_ids": null,
|
|
"begin_suppress_tokens": null,
|
|
"bos_token_id": null,
|
|
"chunk_size_feed_forward": 0,
|
|
"cross_attention_hidden_size": null,
|
|
"decoder_start_token_id": null,
|
|
"depths": [
|
|
2,
|
|
2,
|
|
6,
|
|
2
|
|
],
|
|
"diversity_penalty": 0.0,
|
|
"do_sample": false,
|
|
"drop_path_rate": 0.0,
|
|
"early_stopping": false,
|
|
"enable_fusion": true,
|
|
"enable_patch_fusion": true,
|
|
"enable_patch_layer_norm": true,
|
|
"encoder_no_repeat_ngram_size": 0,
|
|
"eos_token_id": null,
|
|
"exponential_decay_length_penalty": null,
|
|
"finetuning_task": null,
|
|
"flatten_patch_embeds": true,
|
|
"forced_bos_token_id": null,
|
|
"forced_eos_token_id": null,
|
|
"fusion_num_hidden_layers": 2,
|
|
"fusion_type": null,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"initializer_factor": 1.0,
|
|
"is_decoder": false,
|
|
"is_encoder_decoder": false,
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"layer_norm_eps": 1e-05,
|
|
"length_penalty": 1.0,
|
|
"max_length": 20,
|
|
"min_length": 0,
|
|
"mlp_ratio": 4.0,
|
|
"model_type": "clap_audio_model",
|
|
"no_repeat_ngram_size": 0,
|
|
"num_attention_heads": [
|
|
4,
|
|
8,
|
|
16,
|
|
32
|
|
],
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_classes": 527,
|
|
"num_hidden_layers": 4,
|
|
"num_mel_bins": 64,
|
|
"num_return_sequences": 1,
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": null,
|
|
"patch_embed_input_channels": 1,
|
|
"patch_embeds_hidden_size": 96,
|
|
"patch_size": 4,
|
|
"patch_stride": [
|
|
4,
|
|
4
|
|
],
|
|
"prefix": null,
|
|
"problem_type": null,
|
|
"projection_dim": 512,
|
|
"projection_hidden_act": "relu",
|
|
"projection_hidden_size": 768,
|
|
"pruned_heads": {},
|
|
"qkv_bias": true,
|
|
"remove_invalid_values": false,
|
|
"repetition_penalty": 1.0,
|
|
"return_dict": true,
|
|
"return_dict_in_generate": false,
|
|
"sep_token_id": null,
|
|
"spec_size": 256,
|
|
"suppress_tokens": null,
|
|
"task_specific_params": null,
|
|
"temperature": 1.0,
|
|
"tf_legacy_loss": false,
|
|
"tie_encoder_decoder": false,
|
|
"tie_word_embeddings": true,
|
|
"tokenizer_class": null,
|
|
"top_k": 50,
|
|
"top_p": 1.0,
|
|
"torch_dtype": null,
|
|
"torchscript": false,
|
|
"transformers_version": "4.27.0.dev0",
|
|
"typical_p": 1.0,
|
|
"use_bfloat16": false,
|
|
"window_size": 8
|
|
},
|
|
"hidden_size": 768,
|
|
"initializer_factor": 1.0,
|
|
"logit_scale_init_value": 14.285714285714285,
|
|
"model_type": "clap",
|
|
"num_hidden_layers": 16,
|
|
"projection_dim": 512,
|
|
"projection_hidden_act": "relu",
|
|
"text_config": {
|
|
"_name_or_path": "",
|
|
"add_cross_attention": false,
|
|
"architectures": null,
|
|
"attention_probs_dropout_prob": 0.1,
|
|
"bad_words_ids": null,
|
|
"begin_suppress_tokens": null,
|
|
"bos_token_id": 0,
|
|
"chunk_size_feed_forward": 0,
|
|
"classifier_dropout": null,
|
|
"cross_attention_hidden_size": null,
|
|
"decoder_start_token_id": null,
|
|
"diversity_penalty": 0.0,
|
|
"do_sample": false,
|
|
"early_stopping": false,
|
|
"encoder_no_repeat_ngram_size": 0,
|
|
"eos_token_id": 2,
|
|
"exponential_decay_length_penalty": null,
|
|
"finetuning_task": null,
|
|
"forced_bos_token_id": null,
|
|
"forced_eos_token_id": null,
|
|
"fusion_hidden_size": 768,
|
|
"fusion_num_hidden_layers": 2,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"initializer_factor": 1.0,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"is_decoder": false,
|
|
"is_encoder_decoder": false,
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"layer_norm_eps": 1e-12,
|
|
"length_penalty": 1.0,
|
|
"max_length": 20,
|
|
"max_position_embeddings": 514,
|
|
"min_length": 0,
|
|
"model_type": "clap_text_model",
|
|
"no_repeat_ngram_size": 0,
|
|
"num_attention_heads": 12,
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_hidden_layers": 12,
|
|
"num_return_sequences": 1,
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": 1,
|
|
"position_embedding_type": "absolute",
|
|
"prefix": null,
|
|
"problem_type": null,
|
|
"projection_dim": 512,
|
|
"projection_hidden_act": "relu",
|
|
"projection_hidden_size": 768,
|
|
"pruned_heads": {},
|
|
"remove_invalid_values": false,
|
|
"repetition_penalty": 1.0,
|
|
"return_dict": true,
|
|
"return_dict_in_generate": false,
|
|
"sep_token_id": null,
|
|
"suppress_tokens": null,
|
|
"task_specific_params": null,
|
|
"temperature": 1.0,
|
|
"tf_legacy_loss": false,
|
|
"tie_encoder_decoder": false,
|
|
"tie_word_embeddings": true,
|
|
"tokenizer_class": null,
|
|
"top_k": 50,
|
|
"top_p": 1.0,
|
|
"torch_dtype": null,
|
|
"torchscript": false,
|
|
"transformers_version": "4.27.0.dev0",
|
|
"type_vocab_size": 1,
|
|
"typical_p": 1.0,
|
|
"use_bfloat16": false,
|
|
"use_cache": true,
|
|
"vocab_size": 50265
|
|
},
|
|
"torch_dtype": "float32",
|
|
"transformers_version": null
|
|
}
|