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": 58,
+  "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:e7da672f856f8cc23d30075f925ce42ed8015cbdbaccbdc2e1bc137ee43af71a
+size 145404082

special_tokens_map.json

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

tokenizer_config.json

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

tts.py

@@ -0,0 +1,21 @@
+
+from transformers import VitsModel, AutoTokenizer
+import torch
+import numpy as np
+from scipy.io.wavfile import write
+
+model = VitsModel.from_pretrained("tts_urdu")
+tokenizer = AutoTokenizer.from_pretrained("tts_urdu")
+text = "ہیلو، آپ کیسے ہیں؟ میں ٹیکس آفس سے کال کر رہا ہوں۔"
+inputs = tokenizer(text, return_tensors="pt")
+
+inputs["input_ids"] = inputs["input_ids"].long()
+with torch.no_grad():
+    output = model(**inputs).waveform
+
+output = output.squeeze()
+output_np = output.cpu().numpy()
+output_int16 = (output_np * 32767).astype(np.int16)
+write("urdu.wav", rate=model.config.sampling_rate, data=output_int16)
+
+

vocab.json

@@ -0,0 +1,60 @@
+{
+  " ": 26,
+  "'": 4,
+  "0": 48,
+  "1": 36,
+  "2": 24,
+  "3": 20,
+  "4": 35,
+  "5": 8,
+  "6": 51,
+  "7": 27,
+  "8": 7,
+  "9": 23,
+  "_": 30,
+  "آ": 2,
+  "أ": 12,
+  "ؤ": 3,
+  "ئ": 25,
+  "ا": 15,
+  "ب": 31,
+  "ت": 28,
+  "ث": 16,
+  "ج": 49,
+  "ح": 54,
+  "خ": 1,
+  "د": 0,
+  "ذ": 47,
+  "ر": 22,
+  "ز": 44,
+  "س": 57,
+  "ش": 34,
+  "ص": 19,
+  "ض": 42,
+  "ط": 6,
+  "ظ": 32,
+  "ع": 38,
+  "غ": 37,
+  "ف": 29,
+  "ق": 17,
+  "ل": 13,
+  "م": 40,
+  "ن": 9,
+  "و": 10,
+  "ٰ": 39,
+  "ٹ": 46,
+  "پ": 52,
+  "چ": 5,
+  "ڈ": 55,
+  "ڑ": 21,
+  "ژ": 43,
+  "ک": 45,
+  "گ": 14,
+  "ں": 56,
+  "ھ": 41,
+  "ہ": 53,
+  "ۂ": 50,
+  "ی": 18,
+  "ے": 11,
+  "—": 33
+}