Upload 12 files

README.md

@@ -0,0 +1,117 @@
+---
+language:
+- it
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- facebook/voxpopuli
+pipeline_tag: text-to-speech
+base_model: microsoft/speecht5_tts
+model-index:
+- name: SpeechT5-it
+  results:
+  - task:
+      type: text-to-speech
+      name: Text to Speech
+    dataset:
+      name: VOXPOPULI
+      type: facebook/voxpopuli
+      config: it
+      split: validation
+      args: it
+    metrics:
+    - type: loss
+      value: 0.46
+      name: Loss
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SpeechT5-it
+
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VOXPOPULI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4600
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5641        | 1.0   | 712   | 0.5090          |
+| 0.5394        | 2.0   | 1424  | 0.4915          |
+| 0.5277        | 3.0   | 2136  | 0.4819          |
+| 0.5136        | 4.0   | 2848  | 0.4798          |
+| 0.5109        | 5.0   | 3560  | 0.4733          |
+| 0.5078        | 6.0   | 4272  | 0.4731          |
+| 0.5033        | 7.0   | 4984  | 0.4692          |
+| 0.5021        | 8.0   | 5696  | 0.4691          |
+| 0.4984        | 9.0   | 6408  | 0.4670          |
+| 0.488         | 10.0  | 7120  | 0.4641          |
+| 0.491         | 11.0  | 7832  | 0.4641          |
+| 0.4918        | 12.0  | 8544  | 0.4647          |
+| 0.4933        | 13.0  | 9256  | 0.4622          |
+| 0.499         | 14.0  | 9968  | 0.4619          |
+| 0.4906        | 15.0  | 10680 | 0.4608          |
+| 0.4884        | 16.0  | 11392 | 0.4622          |
+| 0.4847        | 17.0  | 12104 | 0.4616          |
+| 0.4916        | 18.0  | 12816 | 0.4592          |
+| 0.4845        | 19.0  | 13528 | 0.4600          |
+| 0.4788        | 20.0  | 14240 | 0.4594          |
+| 0.4746        | 21.0  | 14952 | 0.4607          |
+| 0.4875        | 22.0  | 15664 | 0.4615          |
+| 0.4831        | 23.0  | 16376 | 0.4597          |
+| 0.4798        | 24.0  | 17088 | 0.4595          |
+| 0.4727        | 25.0  | 17800 | 0.4592          |
+| 0.4736        | 26.0  | 18512 | 0.4598          |
+| 0.4746        | 27.0  | 19224 | 0.4608          |
+| 0.4728        | 28.0  | 19936 | 0.4589          |
+| 0.4771        | 29.0  | 20648 | 0.4593          |
+| 0.4743        | 30.0  | 21360 | 0.4588          |
+| 0.4785        | 31.0  | 22072 | 0.4601          |
+| 0.4757        | 32.0  | 22784 | 0.4597          |
+| 0.4731        | 33.0  | 23496 | 0.4598          |
+| 0.4746        | 34.0  | 24208 | 0.4593          |
+| 0.4715        | 35.0  | 24920 | 0.4599          |
+| 0.4769        | 36.0  | 25632 | 0.4622          |
+| 0.4778        | 37.0  | 26344 | 0.4605          |
+| 0.4798        | 38.0  | 27056 | 0.4594          |
+| 0.4694        | 39.0  | 27768 | 0.4607          |
+| 0.468         | 40.0  | 28480 | 0.4600          |
+
+
+### Framework versions
+
+- Transformers 4.30.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

added_tokens.json

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

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
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

gitignore

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdab9df8579635a7d9718f8514d30d3052640352d948b84f3222b908ca54679
+size 585395848

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 sha256:1a12e345a40f2977b27cc65a242df2f1a59ba2ef9bfe120b51c8ea5fba61fec7
+size 585485317

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 +1,11 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 600,
+  "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 sha256:808df4ce9ebf467851b32d7b9e8e6e950bd306c5b98668bcff1845caec220e6b
+size 4155