Upload 6 files

config.json

@@ -0,0 +1,82 @@
+{
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 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,
+  "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,
+  "speaker_embedding_size": 0,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be018653a1c04349ee8dccc51bb905aedd6a6a71548302b7a84ef3475fdf62d4
+size 145394098

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "7",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "spa",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "7",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

usage.py

@@ -0,0 +1,16 @@
+from transformers import VitsModel, AutoTokenizer
+import torch
+import scipy.io.wavfile as wavfile
+
+model = VitsModel.from_pretrained("spanish-tts")
+tokenizer = AutoTokenizer.from_pretrained("spanish-tts")
+text=    "Estoy llamando desde la oficina de impuestos."
+
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    output = model(**inputs).waveform  # Output is a tensor of shape [batch_size, waveform_length]
+
+output_audio = output.squeeze(0).numpy()  # Remove batch dimension
+wavfile.write("spanish.wav", rate=model.config.sampling_rate, data=output_audio)
+

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
+}