Initial commit

README.md

@@ -0,0 +1,37 @@
+# MMS English Male
+
+This model is trained using **IndicTTS dataset** with Hindi male speaker.
+
+## Model
+
+**mms-english-male-indic**: **English model with Hindi male speaker** from the IndicTTS dataset.
+
+## Inference
+
+To use these models for inference, you'll need to install the `transformers` and `accelerate` libraries.
+
+First, install the necessary libraries:
+
+```
+pip install --upgrade transformers accelerate
+```
+
+Then, run inference with the following code-snippet:
+
+```python
+from transformers import VitsModel, AutoTokenizer
+import torch
+from IPython.display import Audio
+
+model_path = "./mms-english-male-indic" # This is the path to your fine-tuned model
+model = VitsModel.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+text = "This is an English model trained using a Hindi male speaker."
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    output = model(**inputs).waveform
+
+Audio(output.numpy(), rate=model.config.sampling_rate)
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 38
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "/opt/data/dhatta/models/mms_tts/finetune-hf-vits/oz_vits_eng",
+  "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": "4.46.2",
+  "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": 38,
+  "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 sha256:336f3e2e3bc9178ddef95d6e5f6c33e9aacebed8b4d69fedc23f1fa2d7cc403e
+size 332160712

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": "k",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "k",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "eng",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "k",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,40 @@
+{
+  " ": 19,
+  "'": 1,
+  "-": 14,
+  "0": 23,
+  "1": 15,
+  "2": 28,
+  "3": 11,
+  "4": 27,
+  "5": 35,
+  "6": 36,
+  "_": 30,
+  "a": 26,
+  "b": 24,
+  "c": 12,
+  "d": 5,
+  "e": 7,
+  "f": 20,
+  "g": 37,
+  "h": 6,
+  "i": 18,
+  "j": 16,
+  "k": 0,
+  "l": 21,
+  "m": 17,
+  "n": 29,
+  "o": 22,
+  "p": 13,
+  "q": 34,
+  "r": 25,
+  "s": 8,
+  "t": 33,
+  "u": 4,
+  "v": 32,
+  "w": 9,
+  "x": 31,
+  "y": 3,
+  "z": 2,
+  "–": 10
+}