Upload best MMS-TTS fine-tune for Adja (Eyaa-Tom)

README.md

@@ -0,0 +1,73 @@
+---
+language:
+- adj
+tags:
+- text-to-speech
+- mms-tts
+- vits
+- adj
+- west-africa
+- eyaa-tom
+- finetuned
+license: cc-by-nc-4.0
+base_model: facebook/mms-tts-adj
+pipeline_tag: text-to-speech
+---
+
+# MMS-TTS Adja — Eyaa-Tom Fine-tuned
+
+Fine-tuned version of [facebook/mms-tts-adj](https://huggingface.co/facebook/mms-tts-adj)
+on the **Eyaa-Tom** dataset for **Adja** (`adj`).
+
+> Adja/Aja-Gbe. Fine-tuned from facebook/mms-tts-adj (closest MMS checkpoint to ISO ajg).
+
+## Language Details
+| Field | Value |
+|-------|-------|
+| Language | Adja |
+| ISO 639-3 (MMS) | `adj` |
+| Your ISO | `ajg` |
+| Region | Togo/Benin |
+| Family | Gbe (Niger-Congo) |
+| Base model | [facebook/mms-tts-adj](https://huggingface.co/facebook/mms-tts-adj) |
+
+## Training Statistics
+| Metric | Value |
+|--------|-------|
+| Training samples | 5 |
+| Validation samples | 1 |
+| Best validation mel-L1 | 3.3801 |
+| Uploaded variant | `best` |
+
+## Usage
+
+```python
+from transformers import VitsModel, VitsTokenizer
+import torch, torchaudio
+
+model     = VitsModel.from_pretrained("Umbaji001/eyaa-tom-mms-tts-adj")
+tokenizer = VitsTokenizer.from_pretrained("Umbaji001/eyaa-tom-mms-tts-adj")
+
+inputs = tokenizer("your text here", return_tensors="pt")
+with torch.no_grad():
+    waveform = model(**inputs).waveform[0]
+
+torchaudio.save("output.wav", waveform.unsqueeze(0), model.config.sampling_rate)
+```
+
+## Training Details
+- **Loss**: Mel-spectrogram L1 (avoids VITS training restriction)
+- **Optimizer**: AdamW — lr=2e-4, betas=(0.8, 0.99)
+- **Scheduler**: ExponentialLR γ=0.999
+- **Epochs**: 6  |  **Batch size**: 4 (effective 16 w/ grad accumulation)
+
+## Citation
+```bibtex
+@article{pratap2023mms,
+  title={Scaling Speech Technology to 1,000+ Languages},
+  author={Pratap, Vineel et al.},
+  journal={arXiv preprint arXiv:2305.13516},
+  year={2023}
+}
+```
+*Fine-tuned: 2026-02-25 — Eyaa-Tom project*

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 46
+}

config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "dtype": "float32",
+  "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,
+  "pad_token_id": null,
+  "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,
+  "transformers_version": "5.0.0",
+  "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": 46,
+  "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 sha256:0d9e521bee58d031589349c67dcb39b9793f787ba966e08504a204a8e8965c2d
+size 145233656

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": null,
+  "backend": "custom",
+  "clean_up_tokenization_spaces": true,
+  "is_local": false,
+  "is_uroman": false,
+  "language": "adj",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,48 @@
+{
+  " ": 45,
+  "'": 10,
+  "-": 26,
+  "a": 1,
+  "b": 12,
+  "c": 20,
+  "d": 22,
+  "e": 2,
+  "f": 24,
+  "g": 19,
+  "h": 32,
+  "i": 8,
+  "j": 23,
+  "k": 7,
+  "l": 6,
+  "m": 5,
+  "n": 4,
+  "o": 13,
+  "p": 25,
+  "r": 18,
+  "s": 11,
+  "t": 21,
+  "u": 17,
+  "v": 39,
+  "w": 15,
+  "y": 14,
+  "z": 43,
+  "|": 0,
+  "à": 37,
+  "á": 31,
+  "è": 42,
+  "é": 33,
+  "ê": 38,
+  "ì": 34,
+  "í": 29,
+  "ò": 35,
+  "ó": 27,
+  "ô": 44,
+  "ù": 40,
+  "ú": 36,
+  "ŋ": 9,
+  "ɔ": 16,
+  "ɛ": 3,
+  "̀": 30,
+  "́": 28,
+  "̂": 41
+}