Dev 2.3. (#242)
* Fix inputs of duration discriminator * Add LSTM * Update models.py * Update tensorboard scalar * Noise injection for minimizing modality gap * Update infer.py * support bf16 run * del unused_para flag * support bf16 config * add grad clip * fix(logger and grad):add dur grad,fix grad clip * Update webui_preprocess.py * Fix English G2P * fix(bert_gen):add pass * Pass SDP to DD * Update webui_preprocess.py * Update config.json * Update webui.py * Update chinese_bert.py * Upload webui for deploy * Update webui.py * torch.save as pt not npy * Update config.json * add freeze emo vq * Update webui_preprocess.py * Fix tone_sandhi.py * Comment up grad clip * Fix in-place addition * Add SLM discriminator * Add DDP for WD * Feat: Style text: make emotions and style similar to the style text by mixing bert (#240) (#241) * fix:(oldVersion210) Load on demand Emotion model * feat: update fastapi.py. 添加更多错误日志信息 * Switch pyopenjtalk to pyopenjtalk-prebuilt * fix: update fastapi.py. 2.2 reference适配 * Update resample.py * 修复Onnx导出的BUG (#237) * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add files via upload * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Delete attentions_onnx.py * Delete models_onnx.py * Add files via upload * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update __init__.py * Update __init__.py * Update __init__.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- * Fix onnx * Format export * Feat: style-text and bert mixing (JA only) * Ensure the same tensor shape * Update * update gradio version * Fix * Style text for chinese and english (ver 2.2) * Style text for chinese and english (ver 2.1) * Style text in FastAPI * Translate style text desc in chinese --------- Co-authored-by: litagin02 <139731664+litagin02@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <40709280+NaruseMioShirakana@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Remove CLAP * Revert "Remove CLAP" This reverts commit 62fd59bc837c580239840a2bc84b15e0663730fc. Revert * Remove CLAP * bf16 audo grad cilp * Update webui and infer utils * Update webui.py * Update webui.py * Update webui-preprocess.py * Update webui_preprocess.py --------- Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: litagin02 <139731664+litagin02@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <40709280+NaruseMioShirakana@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Stardust·减
99
slm/wavlm-base-plus/config.json
Normal file
99
slm/wavlm-base-plus/config.json
Normal file
@@ -0,0 +1,99 @@
|
||||
{
|
||||
"_name_or_path": "wavlm-base-plus",
|
||||
"activation_dropout": 0.0,
|
||||
"adapter_kernel_size": 3,
|
||||
"adapter_stride": 2,
|
||||
"add_adapter": false,
|
||||
"apply_spec_augment": true,
|
||||
"architectures": [
|
||||
"WavLMModel"
|
||||
],
|
||||
"attention_dropout": 0.1,
|
||||
"bos_token_id": 1,
|
||||
"classifier_proj_size": 256,
|
||||
"codevector_dim": 256,
|
||||
"contrastive_logits_temperature": 0.1,
|
||||
"conv_bias": false,
|
||||
"conv_dim": [
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512
|
||||
],
|
||||
"conv_kernel": [
|
||||
10,
|
||||
3,
|
||||
3,
|
||||
3,
|
||||
3,
|
||||
2,
|
||||
2
|
||||
],
|
||||
"conv_stride": [
|
||||
5,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2
|
||||
],
|
||||
"ctc_loss_reduction": "sum",
|
||||
"ctc_zero_infinity": false,
|
||||
"diversity_loss_weight": 0.1,
|
||||
"do_stable_layer_norm": false,
|
||||
"eos_token_id": 2,
|
||||
"feat_extract_activation": "gelu",
|
||||
"feat_extract_norm": "group",
|
||||
"feat_proj_dropout": 0.1,
|
||||
"feat_quantizer_dropout": 0.0,
|
||||
"final_dropout": 0.0,
|
||||
"freeze_feat_extract_train": true,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.1,
|
||||
"hidden_size": 768,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"layerdrop": 0.05,
|
||||
"mask_channel_length": 10,
|
||||
"mask_channel_min_space": 1,
|
||||
"mask_channel_other": 0.0,
|
||||
"mask_channel_prob": 0.0,
|
||||
"mask_channel_selection": "static",
|
||||
"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_min_space": 1,
|
||||
"mask_time_other": 0.0,
|
||||
"mask_time_prob": 0.05,
|
||||
"mask_time_selection": "static",
|
||||
"model_type": "wavlm",
|
||||
"no_mask_channel_overlap": false,
|
||||
"no_mask_time_overlap": false,
|
||||
"num_adapter_layers": 3,
|
||||
"num_attention_heads": 12,
|
||||
"num_buckets": 320,
|
||||
"num_codevector_groups": 2,
|
||||
"num_codevectors_per_group": 320,
|
||||
"num_conv_pos_embedding_groups": 16,
|
||||
"num_conv_pos_embeddings": 128,
|
||||
"num_ctc_classes": 80,
|
||||
"num_feat_extract_layers": 7,
|
||||
"num_hidden_layers": 12,
|
||||
"num_negatives": 100,
|
||||
"output_hidden_size": 768,
|
||||
"pad_token_id": 0,
|
||||
"proj_codevector_dim": 256,
|
||||
"replace_prob": 0.5,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.13.0.dev0",
|
||||
"use_weighted_layer_sum": false,
|
||||
"vocab_size": 32,
|
||||
"tokenizer_class": "Wav2Vec2CTCTokenizer"
|
||||
}
|
||||
Reference in New Issue
Block a user