Subiendo modelo VITS colombiano femenino

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 45
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3bf2550ba5ba4235408b2a84912839cdf9669c5133c9b649060be2572df05e
+size 145288288

checkpoint-500/model_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dad49dc58224a7b209adf39fa7c648fae29f547172a32b3375f6cf2f84462a
+size 187000136

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d40a422cb83e52b46bb096b3069448077edd72a143b4688426af9086a0720e
+size 291083132

checkpoint-500/optimizer_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b9d52e5868d7b1924804b3caced73e83b8aaa5cc68e4b7996485472f6faf50
+size 374071772

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a0764ffa47878a32ae7eccaa886ab7e29c9cf2403a717dc783ff37f83a7f55
+size 14408

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cd88b2d541a562d87e166a2ba925ba92f0cf1185e3844b468e39712226d598
+size 1000

checkpoint-500/scheduler_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd187b318e3bf83063aa293f7c55b8b901fe6050068ba20110fe814ac2dccd21
+size 1008

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "ylacombe/mms-tts-spa-train",
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModelForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "discriminator_kernel_size": 5,
+  "discriminator_period_channels": [
+    1,
+    32,
+    128,
+    512,
+    1024
+  ],
+  "discriminator_periods": [
+    2,
+    3,
+    5,
+    7,
+    11
+  ],
+  "discriminator_scale_channels": [
+    1,
+    16,
+    64,
+    256,
+    1024
+  ],
+  "discriminator_stride": 3,
+  "duration_predictor_dropout": 0.5,
+  "duration_predictor_filter_channels": 256,
+  "duration_predictor_flow_bins": 10,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_num_flows": 4,
+  "duration_predictor_tail_bound": 5.0,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "hop_length": 256,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "leaky_relu_slope": 0.1,
+  "model_type": "vits",
+  "noise_scale": 0.667,
+  "noise_scale_duration": 0.8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 6,
+  "num_speakers": 1,
+  "posterior_encoder_num_wavenet_layers": 16,
+  "prior_encoder_num_flows": 4,
+  "prior_encoder_num_wavenet_layers": 4,
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "sampling_rate": 16000,
+  "segment_size": 8192,
+  "speaker_embedding_size": 0,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    16,
+    16,
+    4,
+    4
+  ],
+  "upsample_rates": [
+    8,
+    8,
+    2,
+    2
+  ],
+  "use_bias": true,
+  "use_stochastic_duration_prediction": true,
+  "vocab_size": 45,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb577dec4591b1236acb80de37a96f1a1958e9b0a3192ddca86bef5436121378
+size 332166088

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "VitsFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 256,
+  "max_wav_value": 32768.0,
+  "n_fft": 1024,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "pad_token": {
+    "content": "7",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tmp/vits_finetuned/runs/Feb02_18-58-22_farid/vits_colombian_spanish_female/1738540919.5627022/events.out.tfevents.1738540919.farid.20396.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307be31b84a1487d0de1694bc3135e05a3f612cf4b6ef6fc72d2ca3304d73f28
+size 7929

tmp/vits_finetuned/runs/Feb02_18-58-22_farid/vits_colombian_spanish_female/1738540919.5721805/hparams.yml

@@ -0,0 +1,144 @@
+accelerator_config: '{''split_batches'': False, ''dispatch_batches'': None, ''even_batches'':
+  True, ''use_seedable_sampler'': True, ''non_blocking'': False, ''gradient_accumulation_kwargs'':
+  None}'
+adafactor: false
+adam_beta1: 0.8
+adam_beta2: 0.99
+adam_epsilon: 1.0e-08
+auto_find_batch_size: false
+average_tokens_across_devices: false
+batch_eval_metrics: false
+bf16: false
+bf16_full_eval: false
+data_seed: None
+dataloader_drop_last: false
+dataloader_num_workers: 0
+dataloader_persistent_workers: false
+dataloader_pin_memory: true
+dataloader_prefetch_factor: None
+ddp_backend: None
+ddp_broadcast_buffers: None
+ddp_bucket_cap_mb: None
+ddp_find_unused_parameters: None
+ddp_timeout: 1800
+debug: '[]'
+deepspeed: None
+disable_tqdm: false
+dispatch_batches: None
+do_eval: true
+do_predict: false
+do_step_schedule_per_epoch: true
+do_train: true
+eval_accumulation_steps: None
+eval_batch_size: 16
+eval_delay: 0
+eval_do_concat_batches: true
+eval_on_start: false
+eval_steps: 25
+eval_strategy: 'no'
+eval_use_gather_object: false
+evaluation_strategy: None
+fp16: false
+fp16_backend: auto
+fp16_full_eval: false
+fp16_opt_level: O1
+fsdp: '[]'
+fsdp_config: '{''min_num_params'': 0, ''xla'': False, ''xla_fsdp_v2'': False, ''xla_fsdp_grad_ckpt'':
+  False}'
+fsdp_min_num_params: 0
+fsdp_transformer_layer_cls_to_wrap: None
+full_determinism: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+gradient_checkpointing_kwargs: None
+greater_is_better: None
+group_by_length: false
+half_precision_backend: auto
+hub_always_push: false
+hub_model_id: vits_colombian_1523_female
+hub_private_repo: None
+hub_strategy: every_save
+hub_token: <HUB_TOKEN>
+ignore_data_skip: false
+include_for_metrics: '[]'
+include_inputs_for_metrics: false
+include_num_input_tokens_seen: false
+include_tokens_per_second: false
+jit_mode_eval: false
+label_names: None
+label_smoothing_factor: 0.0
+learning_rate: 2.0e-05
+length_column_name: length
+load_best_model_at_end: false
+local_rank: 0
+log_level: passive
+log_level_replica: warning
+log_on_each_node: true
+logging_dir: ./tmp/vits_finetuned\runs\Feb02_18-58-22_farid
+logging_first_step: false
+logging_nan_inf_filter: true
+logging_steps: 500
+logging_strategy: steps
+lr_decay: 0.999875
+lr_scheduler_kwargs: '{}'
+lr_scheduler_type: linear
+max_grad_norm: 1.0
+max_steps: 750
+metric_for_best_model: None
+mp_parameters: ''
+neftune_noise_alpha: None
+no_cuda: false
+num_train_epochs: 75
+optim: adamw_torch
+optim_args: None
+optim_target_modules: None
+output_dir: ./tmp/vits_finetuned
+overwrite_output_dir: true
+past_index: -1
+per_device_eval_batch_size: 16
+per_device_train_batch_size: 16
+per_gpu_eval_batch_size: None
+per_gpu_train_batch_size: None
+prediction_loss_only: false
+push_to_hub: true
+push_to_hub_model_id: None
+push_to_hub_organization: None
+push_to_hub_token: <PUSH_TO_HUB_TOKEN>
+ray_scope: last
+remove_unused_columns: true
+report_to: '[''tensorboard'', ''wandb'']'
+restore_callback_states_from_checkpoint: false
+resume_from_checkpoint: None
+run_name: ./tmp/vits_finetuned
+save_on_each_node: false
+save_only_model: false
+save_safetensors: true
+save_steps: 500
+save_strategy: steps
+save_total_limit: None
+seed: 456
+skip_memory_metrics: true
+split_batches: None
+tf32: None
+torch_compile: false
+torch_compile_backend: None
+torch_compile_mode: None
+torch_empty_cache_steps: None
+torchdynamo: None
+tpu_metrics_debug: false
+tpu_num_cores: None
+train_batch_size: 16
+use_cpu: false
+use_ipex: false
+use_legacy_prediction_loop: false
+use_liger_kernel: false
+use_mps_device: false
+warmup_ratio: 0.01
+warmup_steps: 0
+weight_decay: 0.0
+weight_disc: 3
+weight_duration: 1
+weight_fmaps: 1
+weight_gen: 1
+weight_kl: 1.5
+weight_mel: 35

tmp/vits_finetuned/runs/Feb02_18-58-22_farid/vits_colombian_spanish_female/events.out.tfevents.1738540917.farid.20396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee95830221cd40f86d33f59ee339b51319d2335333b1ddad20ab1e34d5c71cb
+size 40127322

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "7",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
+  "is_uroman": false,
+  "language": "spa",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "7",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,47 @@
+{
+  " ": 27,
+  "0": 5,
+  "1": 24,
+  "2": 36,
+  "3": 32,
+  "4": 12,
+  "5": 6,
+  "6": 44,
+  "7": 0,
+  "8": 8,
+  "9": 23,
+  "_": 22,
+  "a": 1,
+  "b": 31,
+  "c": 3,
+  "d": 29,
+  "e": 39,
+  "f": 25,
+  "g": 34,
+  "h": 19,
+  "i": 37,
+  "j": 33,
+  "k": 15,
+  "l": 35,
+  "m": 13,
+  "n": 20,
+  "o": 41,
+  "p": 9,
+  "q": 18,
+  "r": 43,
+  "s": 16,
+  "t": 26,
+  "u": 38,
+  "v": 2,
+  "x": 28,
+  "y": 10,
+  "z": 11,
+  "á": 17,
+  "é": 21,
+  "í": 30,
+  "ñ": 42,
+  "ó": 7,
+  "ú": 40,
+  "ü": 14,
+  "—": 4
+}