Training in progress, step 200

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 86
+}

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "MBZUAI/speecht5_tts_clartts_ar",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "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
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "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": 1876,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 98
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0661da694d297ff7e8a0214625896108415d855adc08c8d4ff3e52c96fc2da20
+size 577841544

runs/May25_17-30-48_8c963fad3cd1/events.out.tfevents.1716658257.8c963fad3cd1.693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643d9a2f25665e275ce5a21be8c582de40f080cffc673ecff210ae8d45393354
+size 6498

runs/May25_17-31-32_8c963fad3cd1/events.out.tfevents.1716658299.8c963fad3cd1.693.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5ac8f306f03e685037721bf5e093b4a2a4cef10f22286d5e3cab19f9765445
+size 6497

runs/May25_17-32-11_8c963fad3cd1/events.out.tfevents.1716658337.8c963fad3cd1.693.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65505ec097e9901a15e2233c7c133ecef3081f5fdcc1210f62ec7fec83ec6db2
+size 14574

runs/May25_17-40-34_8c963fad3cd1/events.out.tfevents.1716658844.8c963fad3cd1.693.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4272243411d98ba1be77c0045dc8b7336b6f3f0b7941b117f6423bef82230741
+size 12904

runs/May25_18-00-55_8c963fad3cd1/events.out.tfevents.1716660063.8c963fad3cd1.693.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e527410e56d9adcd91a7a31823d1b0ac5c3b9a0229b645190a2cb43fdfee430d
+size 19312

runs/May25_18-07-13_8c963fad3cd1/events.out.tfevents.1716660439.8c963fad3cd1.693.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a641a220494fac6eaa29103f2fbc990a24065c77136882e127cb251a416558e
+size 8436

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4b56b4bbf0637c59a5c9c8531362bf8ce2bcde4fcd28ce0a0ec26cdf70a905
+size 403344

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf4addaf09bd4c492fd4af97c66e6f1880505f9151b4e86ff9d240cf97c082c
+size 5304