Duplicate from alakxender/mms-tts-div-finetuned-md-m02

Co-authored-by: rusputin <alakxender@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+outputs/audio/001.wav filter=lfs diff=lfs merge=lfs -text
+outputs/spectrograms/001.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+tags:
+- dhivehi-tts
+license: mit
+datasets:
+- alakxender/dv_syn_speech_md
+language:
+- dv
+base_model:
+- facebook/mms-tts-div
+---
+
+# Divehi TTS – Male Voice (VITS-based)
+
+This is a fine-tuned VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) model for Divehi speech synthesis. The model produces Male voice audio from Thaana-scripted Divehi text. Fine-tuned from Meta’s MMS-TTS architecture using a curated dataset of synthetic Divehi speech.
+
+## Model Details
+
+| Field                 | Value                                           |
+|----------------------|-------------------------------------------------|
+| **Model ID**         | `alakxender/mms-tts-div-finetuned-md-m02`       |
+| **Base Architecture**| MMS-TTS (VITS)                                  |
+| **Language**         | Divehi (dv)                                     |
+| **Voice**            | Male                                            |
+| **Sampling Rate**    | 16 kHz                                          |
+| **Tokenizer**        | VITSTokenizer                                   |
+| **Inference Engine** | Transformers (🤗 Hugging Face)                  |
+
+
+## Usage
+
+```python
+from transformers import VitsModel, VitsTokenizer
+import torchaudio
+
+tokenizer = VitsTokenizer.from_pretrained("alakxender/mms-tts-div-finetuned-md-m02")
+model = VitsModel.from_pretrained("alakxender/mms-tts-div-finetuned-md-m02")
+
+text = "މޫސުން ވަރަށް ގޯސްވެ، ފުވައްމުލަކުން ފެށިގެން އައްޑުއަށް އޮރެންޖް އެލާޓް ނެރެފި"
+inputs = tokenizer(text, return_tensors="pt")
+waveform = model.generate(**inputs).waveform[0]
+
+torchaudio.save("output.wav", waveform.unsqueeze(0), 16000)
+```
+
+## Evaluation Summary
+
+- **Model**: `alakxender/mms-tts-div-finetuned-md-m02`
+- **Evaluated Samples**: 3
+- **Avg Estimated MOS (UTMOS)**: `2.926`
+  ```json
+  {
+    "5": "Excellent (very natural)",
+    "4": "Good (mostly natural)",
+    "3": "Fair (some robotic quality)",
+    "2": "Poor (noticeably unnatural)",
+    "1": "Bad (unintelligible or very synthetic)"
+  }
+  ```
+- **Artifacts**:
+  - 🎵 Audio: `outputs/audio/`
+  - 📊 Spectrograms: `outputs/spectrograms/`
+  - 📄 Report: `outputs/report.txt`
+  - 📈 MOS Scores: `outputs/mos_scores.txt`
+
+## Acknowledgements
+
+- [Meta MMS-TTS](https://github.com/facebookresearch/fairseq/tree/main/examples/mms)
+- [Tarepan's SpeechMOS](https://github.com/Tarepan/SpeechMOS)
+- [Hugging Face 🤗 Transformers](https://huggingface.co/transformers/)
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 53
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "./tmp/vits_finetuned_div-m02",
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "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": "4.40.2",
+  "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": 53,
+  "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 sha256:5afd715b694cb5899c6093fd1d91b797cedb5a2cf51c2418a739e248afd9cd50
+size 145242232

outputs/audio/001.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eeca5b825cdf0dde4a575f1e2b09ae0854d4d42a98d2d9f6caeaece68621f53
+size 108622

outputs/mos_scores.txt

@@ -0,0 +1,4 @@
+001.wav	2.868
+002.wav	2.754
+003.wav	3.157
+Avg MOS	2.926

outputs/report.txt

@@ -0,0 +1,3 @@
+001	އީދު ފާހަގަކުރުމުގައި ހުއްދަ މުނިފޫހިފިލުވުމަކީ ކޮބާ؟	./outputs/audio/001.wav	./outputs/spectrograms/001.png
+002	އައިންމަތީ ދޫނި މަދުވެއްޖެ، ތޭރަވާ ގެއްލިއްޖެ	./outputs/audio/002.wav	./outputs/spectrograms/002.png
+003	"ނުކުމެވޭ ވަރެއް ނޫން، މަގުތައް ބުޅާ ނަޖިހުން ފުރިފައި"	./outputs/audio/003.wav	./outputs/spectrograms/003.png

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": "|",
+    "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": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "div",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,55 @@
+{
+  " ": 52,
+  "'": 43,
+  "|": 0,
+  "ا": 47,
+  "ل": 45,
+  "ه": 48,
+  "ހ": 14,
+  "ށ": 22,
+  "ނ": 5,
+  "ރ": 13,
+  "ބ": 19,
+  "ޅ": 25,
+  "ކ": 9,
+  "އ": 3,
+  "ވ": 10,
+  "މ": 12,
+  "ފ": 18,
+  "ދ": 17,
+  "ތ": 16,
+  "ލ": 21,
+  "ގ": 11,
+  "ޏ": 37,
+  "ސ": 20,
+  "ޑ": 27,
+  "ޒ": 35,
+  "ޓ": 33,
+  "ޔ": 26,
+  "ޕ": 31,
+  "ޖ": 29,
+  "ޗ": 38,
+  "ޘ": 51,
+  "ޙ": 30,
+  "ޚ": 39,
+  "ޛ": 49,
+  "ޝ": 40,
+  "ޞ": 41,
+  "ޟ": 44,
+  "ޠ": 50,
+  "ޡ": 46,
+  "ޢ": 36,
+  "ޣ": 42,
+  "ޤ": 34,
+  "ަ": 1,
+  "ާ": 8,
+  "ި": 7,
+  "ީ": 15,
+  "ު": 6,
+  "ޫ": 28,
+  "ެ": 2,
+  "ޭ": 23,
+  "ޮ": 24,
+  "ޯ": 32,
+  "ް": 4
+}