Upload 6 files

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "facebook/mms-tts-ara",
+  "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": "4.33.2",
+  "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": 39,
+  "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 sha256:34d1ae05a8e6f865e7c8e355a23d626a3fe5ebd8f640849cf37a75d5e33f3314
+size 145389045

special_tokens_map.json

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

tokenizer_config.json

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

tts.py

@@ -0,0 +1,20 @@
+from transformers import VitsModel, AutoTokenizer
+import torch
+import numpy as np
+from scipy.io.wavfile import write
+
+model = VitsModel.from_pretrained("tts_arabic")
+tokenizer = AutoTokenizer.from_pretrained("SeyedAli/Arabic-Speech-synthesis")
+
+text = "عشر ديما خمسة وعشرين رجلا في ليلة واحدة ومن ثم قام بقتلها"
+text = "يوفر مجتمع البناء قروضا عقارية وقروض وعقارية"
+inputs = tokenizer(text, return_tensors="pt")
+
+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("arabic.wav", rate=model.config.sampling_rate, data=output_int16)
+

vocab.json

@@ -0,0 +1,41 @@
+{
+  " ": 25,
+  "_": 37,
+  "ء": 26,
+  "آ": 27,
+  "أ": 20,
+  "ؤ": 35,
+  "إ": 4,
+  "ئ": 38,
+  "ا": 0,
+  "ب": 28,
+  "ة": 7,
+  "ت": 12,
+  "ث": 19,
+  "ج": 13,
+  "ح": 23,
+  "خ": 11,
+  "د": 16,
+  "ذ": 6,
+  "ر": 9,
+  "ز": 34,
+  "س": 8,
+  "ش": 32,
+  "ص": 18,
+  "ض": 22,
+  "ط": 10,
+  "ظ": 14,
+  "ع": 3,
+  "غ": 5,
+  "ف": 36,
+  "ق": 33,
+  "ك": 2,
+  "ل": 31,
+  "م": 30,
+  "ن": 1,
+  "ه": 24,
+  "و": 29,
+  "ى": 21,
+  "ي": 15,
+  "–": 17
+}