Training in progress, step 1000

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}

config.json

@@ -0,0 +1,91 @@
+{
+  "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,
+  "dtype": "float32",
+  "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": null,
+  "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,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": [
+    2
+  ],
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7215769fd450e43946aefd0d911c5fb4821a647ef06a21e8eec8026786e90f
+size 577789320

runs/Oct27_10-17-05_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761556634.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1693e1ce3118815321b34384f0e3b2e62ca15ca2727490fc50b6af13e5aeb5eb
+size 6637

runs/Oct27_10-18-33_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761556715.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e2f536eebafe35f32f58f1214a751ee20b941699acc157fb5332716e975a26
+size 6636

runs/Oct27_10-19-31_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761556773.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1dad8aaf6f109e4ec42b00979fdf4d86a2c241b4b909d3efa8e9cae2931ce7
+size 6636

runs/Oct27_10-20-48_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761556850.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c9255af855f668c3336af4a133ce6e9f00a3a0c9396e77540c448bae379eaf
+size 6632

runs/Oct27_10-51-43_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558706.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54952f3fa58bbb39ea237a809d7250370087e63bc1d6fcf5036e80e485637a08
+size 6631

runs/Oct27_10-51-43_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558783.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c03d0dd4b6ecc21e7330ddf16d5fc1e5b072b9578d0e593d1677000577a9a21
+size 6631

runs/Oct27_10-53-30_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558814.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5ed71d2e3be31487033d85a74b0d8adc838e7e1baeeabc0dd021d2b033f572
+size 6632

runs/Oct27_10-55-38_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558942.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94108cb4ce08b1037cbd7d7e0156a85e74da9ca43fbd5eac7a79be311a98034e
+size 6632

runs/Oct27_10-55-59_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558961.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f824b0ee609185e70ca938575973903d11486ee15df1744ed5c4334b357025
+size 6633

runs/Oct27_10-56-14_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761558976.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cc97df9154e948be8ed15d2c2d5740142f6ae5483df6e86ae77903d48cdb74
+size 6631

runs/Oct27_10-56-47_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761559011.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c66c7801a6d0f82c12445635eb53c624d9bce3300d5adaa176147c76b7d6e80
+size 6632

runs/Oct27_10-59-43_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761559187.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d009bbe59746044abdbdcf4d390028c670e626930fd2927659b9eb4dac7d8056
+size 6632

runs/Oct27_11-01-17_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761559284.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe67387b7ee3d4656582c8c99fd56470fa2ccdc3d4a2efca464558004176725c
+size 6632

runs/Oct27_11-02-27_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761559351.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c4f0ba9252f37f75fc6e4da6e1e814e13d2b65355851ffde2fd24b1a1155f1
+size 6632

runs/Oct27_11-05-06_r-technotron-trainer-0widy16f-65af2-vb4tz/events.out.tfevents.1761559509.r-technotron-trainer-0widy16f-65af2-vb4tz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abdb783d335db438ad236d7e2974ba3f0a07082058f7be66916b22ba7624b3c
+size 8767

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 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "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:cc56af2e51780b7659f079d02dd25a8becdd142e303d75b75a0915b42676782a
+size 6097