Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,145 @@
+---
+# All 22 scheduled Indian languages + English TTS model
+language:
+  - hi
+  - bn
+  - mr
+  - te
+  - kn
+  - mai
+  - as
+  - brx
+  - doi
+  - gu
+  - ml
+  - pa
+  - ta
+  - ne
+  - sa
+  - sat
+  - sd
+  - or
+  - mni
+  - ks
+  - kok
+  - ur
+  - en
+base_model: Aratako/MioTTS-0.6B
+library_name: transformers
+model_name: Indic-Mio
+pipeline_tag: text-to-speech
+tags:
+  - speech
+  - tts
+  - voice
+licence: apache-2.0
+---
+
+# Model Card for Indic-Mio
+
+<b>Indic-Mio</b> is an open-source Text-to-Speech (TTS) model that supports all <b>22 scheduled Indian languages and English</b>. Produces high-quality natural-sounding speech at <b>44kHz</b> with less than <b>0.1 RTF</b>. Zero-shot voice cloning supported via speaker embeddings in the codec. Also works well for code-mixed sentences.
+
+This model is a fine-tuned version of [Aratako/MioTTS-0.6B](https://huggingface.co/Aratako/MioTTS-0.6B) which uses [MioCodec](https://huggingface.co/Aratako/MioCodec-25Hz-24kHz) for speech tokenization.
+<!-- It has been trained using Transformers, Unsloth and [TRL](https://github.com/huggingface/trl). -->
+
+
+## Prompting
+
+For emotion and style control, place the tags <b>at the end</b> of the sentence.
+
+For example: `मुझे यह फिल्म बहुत पसंद आई! <happy>` or `I am not sure if I can do this. <confused>`
+
+Tags for Indian languages: `<happy>`, `<sad>`, `<angry>`, `<disgust>`, `<fear>`, `<surprise>` <br>
+Tags for English: `<happy>`, `<sad>`, `<enunciated>`, `<confused>`, `<angry>`, `<whisper>`
+
+A word can be stressed by using asterisks(*) around it. For example: `No! I could *never* do it!`
+
+## Inference
+
+<b>Approach 1: With MioTTS-Inference (recommended)</b>
+
+Install [vllm](https://github.com/vllm-project/vllm) and set up [MioTTS-Inference](https://github.com/Aratako/MioTTS-Inference).
+
+```bash
+vllm serve SPRINGLab/Indic-Mio --max-model-len 1024 --gpu-memory-utilization 0.5
+```
+
+```bash
+cd MioTTS-Inference
+MIOTTS_CODEC_MODEL=Aratako/MioCodec-25Hz-44.1kHz-v2 \
+MIOTTS_LLM_BASE_URL=http://localhost:8000/v1 \
+python run_server.py --host 0.0.0.0 --port 8001
+```
+
+```bash
+GRADIO_SERVER_PORT=7861 \
+MIOTTS_API_BASE=http://127.0.0.1:8001 \
+python run_gradio.py
+```
+
+<b>Approach 2: Directly with Transformers</b>
+
+```bash
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from miocodec import MioCodec
+import numpy as np
+import torch
+
+model_name = "SPRINGLab/Indic-Mio"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, torch_dtype=torch.bfloat16, device_map="cuda"
+)
+
+text = "नमस्ते, आप कैसे हैं?"
+messages = [{"role": "user", "content": text}]
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+output = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+    temperature=0.9,
+    top_p=0.9,
+)
+
+generated = output[0][inputs["input_ids"].shape[1]:]
+speech_offset = 151669
+audio_codes = [t.item() - speech_offset for t in generated 
+               if speech_offset <= t.item() < speech_offset + 12800]
+
+# Convert audio_codes by decoding with MioCodec
+# audio_codes -> numpy array -> MioCodec decode -> wav
+
+codec = MioCodec.from_pretrained("Aratako/MioCodec-25Hz-24kHz")
+codes_tensor = torch.tensor([audio_codes], dtype=torch.long).unsqueeze(0)  # [1, 1, T]
+wav = codec.decode(codes_tensor)  # -> [1, 1, num_samples]
+
+import soundfile as sf
+sf.write("output.wav", wav.squeeze().cpu().numpy(), 44100)
+
+```
+
+## Training
+
+This model was trained on a single NVIDIA A6000 ADA GPU in less than 6 hours.
+
+For Indian languages, IndicTTS, Rasa and Syspin datasets were used. For American English, LibriTTS and Expresso, while for Indian English, SPICOR dataset was used.
+
+## Fine-tuning
+
+This model is robust yet flexible. You can fine-tune it on your own dataset for better performance on specific languages, accents, speakers, styles or emotions. Just a few steps of LoRA fine-tuning can significantly improve the performance for your target task.
+
+## Citations
+
+In case you use this model, please cite this huggingface repository as follows:
+
+```bibtex
+@misc{indic-mio-tts,
+  title={Indic-Mio TTS},
+  author={Advait Joglekar},
+  year={2026},
+  publisher = {Hugging Face},
+  howpublished={\url{https://huggingface.co/SPRINGLab/Indic-Mio}},
+}
+```

chat_template.jinja

@@ -0,0 +1,6 @@
+{%- for message in messages %}
+{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{ '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "unsloth_version": "2026.2.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 164480
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065f42f7ab6148b66f43e9be0d01ac336343dfe16161350c37b71a87c3e1981b
+size 1217825224

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcde038b87ccd029a4523b0c5cec1da6d84b4f3d68b351495df086d63033f1f
+size 13817944