Training in progress, epoch 10

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "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": "4.42.3",
+  "use_cache": true,
+  "use_guided_attention_loss": true,
+  "vocab_size": 96
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb3a2eaa48ac999926b4c85907532dbdaa64f620acbf58ade7055c3fee74656
+size 577835400

runs/Jul27_20-07-24_Hamza/events.out.tfevents.1722092888.Hamza.24420.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6014f0087a8515e067e830fb359c7506295d7b391aa2e5d6063fc55932464455
+size 6479

runs/Jul27_20-21-40_Hamza/events.out.tfevents.1722093742.Hamza.28544.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3dcccf548eb79fd6c061956bc13b66b546d7260927ba541ef6e2bd1d75b509
+size 6479

runs/Jul28_14-44-09_Hamza/events.out.tfevents.1722159869.Hamza.12840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2da56047e749ef1ea5d246740b351dc474eeb504be64775718b681bcab9936
+size 6479

runs/Jul28_15-25-33_Hamza/events.out.tfevents.1722162340.Hamza.17820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b8bca06bf1011bd03fe4f2212147aef65514941025bba1a9d74b7115830578
+size 6478

runs/Jul28_15-44-46_Hamza/events.out.tfevents.1722163494.Hamza.5788.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c854f3ecefbdec91f31fcb83377d7aa5e2fc82474cf98fc7aeca55b48a1731b9
+size 9412

runs/Jul28_15-45-47_Hamza/events.out.tfevents.1722163552.Hamza.5788.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0cf8c456c41535897e150d9bee94e38bb67ed891ed2a03da1bc172867b8377
+size 50102

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39be9c4c94721df3e88eca7c786d9af62ac8fe403466e4500b1d8a5a18457fa
+size 5304