Training in progress, step 5000

added_tokens.json

@@ -0,0 +1,76 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79,
+  "ँ": 115,
+  "ं": 105,
+  "ः": 87,
+  "अ": 114,
+  "अं": 122,
+  "अः": 143,
+  "आ": 85,
+  "इ": 97,
+  "ई": 144,
+  "उ": 130,
+  "ऊ": 82,
+  "ऋ": 145,
+  "ए": 86,
+  "ऐ": 108,
+  "ओ": 81,
+  "औ": 116,
+  "क": 152,
+  "क्ष": 94,
+  "ख": 148,
+  "ग": 149,
+  "घ": 102,
+  "ङ": 141,
+  "च": 110,
+  "छ": 101,
+  "ज": 126,
+  "ज्ञ": 109,
+  "झ": 95,
+  "ञ": 83,
+  "ट": 111,
+  "ठ": 103,
+  "ड": 90,
+  "ढ": 99,
+  "ण": 138,
+  "त": 96,
+  "त्र": 120,
+  "थ": 84,
+  "द": 106,
+  "ध": 134,
+  "न": 123,
+  "प": 151,
+  "फ": 135,
+  "ब": 147,
+  "भ": 107,
+  "म": 88,
+  "य": 129,
+  "र": 132,
+  "ल": 150,
+  "व": 146,
+  "श": 89,
+  "ष": 104,
+  "स": 112,
+  "ह": 113,
+  "़": 100,
+  "ा": 137,
+  "ि": 121,
+  "ी": 139,
+  "ु": 136,
+  "ू": 131,
+  "ृ": 127,
+  "ॄ": 125,
+  "ॅ": 124,
+  "ॆ": 140,
+  "े": 128,
+  "ै": 133,
+  "ॉ": 119,
+  "ॊ": 98,
+  "ो": 92,
+  "ौ": 142,
+  "्": 91,
+  "ॐ": 93,
+  "॑": 118,
+  "ॠ": 117
+}

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": "4.33.0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 153
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa7dfaec5fd15e99eec314cffff73d7fb8a442eb0a47a0bc9b4095817c25bd8
+size 578099962

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 600,
+  "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 sha256:53f1e091958ba613a1ecbcce6602c084cc4364a07a743858cf9bf8d50e677ffb
+size 4728