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": 72,
+  "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 sha256:9976bca6a9d1fb449e730b69076369612afee3394a71a5a9f75df955650350f6
+size 145414834

special_tokens_map.json

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

tokenizer_config.json

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

tts.py

@@ -0,0 +1,22 @@
+from transformers import VitsModel, AutoTokenizer
+import torch
+import numpy as np
+from scipy.io.wavfile import write
+
+model = VitsModel.from_pretrained("tts_hindi")
+tokenizer = AutoTokenizer.from_pretrained("tts_hindi")
+
+i = 1
+with open('transcription.txt', 'r', encoding='utf-8') as file:
+    for line in file:
+     # text = "नमस्ते, आप कैसे हैं? मैं टैक्स ऑफिस से बोल रहा हूँ"
+      text = line
+      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("hindi/"+str(i)+".wav", rate=model.config.sampling_rate, data=output_int16)
+      i = i+1

vocab.json

@@ -0,0 +1,74 @@
+{
+  " ": 7,
+  "'": 44,
+  "-": 3,
+  "0": 8,
+  "1": 2,
+  "2": 18,
+  "3": 25,
+  "4": 1,
+  "8": 6,
+  "_": 33,
+  "`": 45,
+  "ँ": 16,
+  "ं": 30,
+  "ः": 35,
+  "अ": 4,
+  "आ": 55,
+  "इ": 5,
+  "ई": 34,
+  "उ": 32,
+  "ऊ": 65,
+  "ए": 11,
+  "ऐ": 12,
+  "ऑ": 19,
+  "ओ": 67,
+  "औ": 60,
+  "क": 70,
+  "ख": 42,
+  "ग": 49,
+  "घ": 47,
+  "च": 17,
+  "छ": 9,
+  "ज": 57,
+  "झ": 58,
+  "ञ": 26,
+  "ट": 68,
+  "ठ": 29,
+  "ड": 56,
+  "ढ": 50,
+  "ण": 43,
+  "त": 69,
+  "थ": 20,
+  "द": 62,
+  "ध": 37,
+  "न": 10,
+  "प": 48,
+  "फ": 0,
+  "ब": 41,
+  "भ": 21,
+  "म": 71,
+  "य": 51,
+  "र": 39,
+  "ल": 38,
+  "व": 46,
+  "श": 59,
+  "ष": 14,
+  "स": 40,
+  "ह": 36,
+  "़": 13,
+  "ा": 54,
+  "ि": 15,
+  "ी": 22,
+  "ु": 28,
+  "ू": 66,
+  "ृ": 63,
+  "ॅ": 24,
+  "े": 52,
+  "ै": 27,
+  "ॉ": 31,
+  "ो": 61,
+  "ौ": 64,
+  "्": 53,
+  "‍": 23
+}