v1.0

Signed-off-by: jjyaoao <jjyaoao@126.com>

.gitignore

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

README.md

@@ -1,3 +1,81 @@
 ---
-license: apache-2.0
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- voxpopuli
+model-index:
+- name: speecht5_finetuned_facebook_voxpopuli_spanish
+  results: []
+pipeline_tag: text-to-speech
 ---
+
+<!-- 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_finetuned_facebook_voxpopuli_spanish
+
+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: 0.4355
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.484         | 1.0   | 1074  | 0.4623          |
+| 0.4724        | 2.0   | 2148  | 0.4542          |
+| 0.4646        | 3.0   | 3222  | 0.4474          |
+| 0.463         | 4.0   | 4296  | 0.4451          |
+| 0.4538        | 5.0   | 5370  | 0.4425          |
+| 0.4509        | 6.0   | 6444  | 0.4408          |
+| 0.4548        | 7.0   | 7518  | 0.4412          |
+| 0.4465        | 8.0   | 8592  | 0.4389          |
+| 0.4509        | 9.0   | 9666  | 0.4387          |
+| 0.4424        | 10.0  | 10740 | 0.4369          |
+| 0.4415        | 11.0  | 11814 | 0.4367          |
+| 0.4386        | 12.0  | 12888 | 0.4366          |
+| 0.4383        | 13.0  | 13962 | 0.4357          |
+| 0.4396        | 14.0  | 15036 | 0.4348          |
+| 0.4432        | 15.0  | 16110 | 0.4358          |
+| 0.4378        | 16.0  | 17184 | 0.4356          |
+| 0.4321        | 17.0  | 18258 | 0.4353          |
+| 0.4381        | 18.0  | 19332 | 0.4353          |
+| 0.4325        | 19.0  | 20406 | 0.4347          |
+| 0.4336        | 20.0  | 21480 | 0.4355          |
+
+
+### 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
+}

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:fbbe15963a918045b0b85d589cdbe2c5ec4e20ab9ad7b43d6f3fd1a2c02c72d8
+size 585485317

runs/Jul15_01-52-20_c29dfb936ef1/1689385951.5689578/events.out.tfevents.1689385951.c29dfb936ef1.575119.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1cabcfd944c55fe4b055bb3542aa9e8fc734b3469b3fad6b0226da739ffb525
+size 6287

runs/Jul15_01-52-20_c29dfb936ef1/events.out.tfevents.1689385951.c29dfb936ef1.575119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46e7d74da308bddc01dd3aeed5fbfd53271373c443b9dc4321653754dadf967
+size 146998

runs/Jul15_09-56-10_c29dfb936ef1/1689414991.924351/events.out.tfevents.1689414991.c29dfb936ef1.575119.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907603e2dbd51efe27e5e041025e7f67d482b0d616049838fd28605f2312c75a
+size 6287

runs/Jul15_09-56-10_c29dfb936ef1/events.out.tfevents.1689414991.c29dfb936ef1.575119.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba53a365b804d48f22e037fa7e153df9b3f64ca28a2d002276064d34456cda9
+size 146998

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 sha256:04857f203617ade08b849395f8d1bc2bab8ef3020930eb1a30d414ad55ee7935
+size 4155