Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.30.0.dev0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde01b016a1b1b01e68e3fda3ae14b16233010e991d9690b8e0d57a153595d75
+size 585485317

runs/Jun26_19-45-51_abdulrahman-MS-7D99/events.out.tfevents.1687797962.abdulrahman-MS-7D99.1391349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9d125c8516513f3d02c4ef3377ee850da0e0f0ac37a2fe43b17f11b31791ff
+size 5698

runs/Jun26_19-51-10_abdulrahman-MS-7D99/1687798276.59071/events.out.tfevents.1687798276.abdulrahman-MS-7D99.1392299.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc36e56648182c652841bbe24ea969a49169952d307a2469d8e0394ebfd594d
+size 6220

runs/Jun26_19-51-10_abdulrahman-MS-7D99/events.out.tfevents.1687798276.abdulrahman-MS-7D99.1392299.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf9509b6bd6fb8438f904d1e259824e785503d6a7d002341ce180c249b940f3
+size 5669

runs/Jun26_19-57-02_abdulrahman-MS-7D99/1687798658.7372935/events.out.tfevents.1687798658.abdulrahman-MS-7D99.1392844.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18659460494e52e0fc917432ed2cd7b9871a04cb397fc8355a033d378d4f2af
+size 6220

runs/Jun26_19-57-02_abdulrahman-MS-7D99/events.out.tfevents.1687798658.abdulrahman-MS-7D99.1392844.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa786a4e27c3c7c6551f3bcf0231ca30a2647c33e28710d4ecda0072b2aa0d5
+size 5669

runs/Jun26_20-03-27_abdulrahman-MS-7D99/1687799012.3455267/events.out.tfevents.1687799012.abdulrahman-MS-7D99.1393581.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2630aad20b57d7be07d87fd09d824b425fa013ab7cf5aeef3d21769a5a648a8
+size 6220

runs/Jun26_20-03-27_abdulrahman-MS-7D99/events.out.tfevents.1687799012.abdulrahman-MS-7D99.1393581.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1115f20f731b6688defc30f2c91220dba18542215729ea05732613e69c3af317
+size 5669

runs/Jun28_13-52-08_abdulrahman-MS-7D99/1687949534.6496582/events.out.tfevents.1687949534.abdulrahman-MS-7D99.1394159.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e4439757c976a0d8e4814ea1f70958af0cd1cf435f6730f75475b3ae0658f5
+size 6220

runs/Jun28_13-52-08_abdulrahman-MS-7D99/events.out.tfevents.1687949534.abdulrahman-MS-7D99.1394159.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcab4d9914ff6b6aefca54b98cbc9e43c1c5a8752177c963bd9ec29d7718daea
+size 12205

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 sha256:700ff3136089aa4e3fbb18e7c3d13bde9cebe873891d4bfb79878a6a4a5d25e2
+size 238198

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "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 sha256:27536f7b65b33616b52319e28d337d2cb3e2b6b3a44310d5cda0670841cf0b4c
+size 4155