Training in progress, step 100

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: nonoJDWAOIDAWKDA/speecht5_finetuned_nono
+base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_nono
 
-This model is a fine-tuned version of [nonoJDWAOIDAWKDA/speecht5_finetuned_nono](https://huggingface.co/nonoJDWAOIDAWKDA/speecht5_finetuned_nono) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5761
+- Loss: 0.6025
 
 ## Model description
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - lr_scheduler_warmup_steps: 100
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.4141        | 16.6667 | 100  | 0.5827          |
-| 0.4192        | 33.3333 | 200  | 0.5684          |
-| 0.4133        | 50.0    | 300  | 0.5686          |
-| 0.4028        | 66.6667 | 400  | 0.5810          |
-| 0.3954        | 83.3333 | 500  | 0.5761          |
+| 0.6064        | 16.6667 | 100  | 0.5937          |
+| 0.5045        | 33.3333 | 200  | 0.5903          |
+| 0.481         | 50.0    | 300  | 0.5985          |
+| 0.4639        | 66.6667 | 400  | 0.5867          |
+| 0.4483        | 83.3333 | 500  | 0.6025          |
 
 
 ### Framework versions
 
-- Transformers 4.45.0
-- Pytorch 2.4.1+cu118
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
 - Datasets 3.1.0
 - Tokenizers 0.20.0

added_tokens.json

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

config.json

@@ -1,92 +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": 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,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
-  "use_cache": false,
-  "use_guided_attention_loss": true,
-  "vocab_size": 81
-}
+{
+  "_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": 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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18841d2888c2916ce69b389f5813a997a338452262a81ee9cd6ab321c34e8b66
+oid sha256:a4ccb5b0c3c46fb621240e5a0f6adb5313b8bf9f6700c950bf6401da7790c951
 size 577789320

preprocessor_config.json

@@ -1,19 +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
-}
+{
+  "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
+}

runs/Nov15_16-37-46_HerLolipop/events.out.tfevents.1731663468.HerLolipop.36500.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60936ac6e558ae00b9eedb8578afbf9bfe2159995971dc4e2253abfdec8d795
+size 12600

runs/Nov15_16-59-23_HerLolipop/events.out.tfevents.1731664764.HerLolipop.36500.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a648d2a58db39e7514600fae1d2c5b77d43ac8f0180bda8423e53ddbc09f9bc
+size 7790

special_tokens_map.json

@@ -1,13 +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>"
-}
+{
+  "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>"
+}

tokenizer_config.json

@@ -1,63 +1,63 @@
-{
-  "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>",
-  "mask_token": "<mask>",
-  "model_max_length": 600,
-  "normalize": false,
-  "pad_token": "<pad>",
-  "processor_class": "SpeechT5Processor",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "SpeechT5Tokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "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>",
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b39412a59446e659df37512b69437cfe7d449833b2a2d63d47f379a39ca741
+oid sha256:de0943a68866e7bd340ca3fb35234afe0366e2abfb42fb22dc57ba704c5dde93
 size 5432