--- language: - bho - hi license: apache-2.0 tags: - text-to-speech - tts - mlx - parler-tts - bhojpuri - lora - apple-silicon - indic-languages base_model: ai4bharat/indic-parler-tts --- # Indic Parler TTS — Bhojpuri LoRA (MLX) **First MLX implementation of Parler TTS**, fine-tuned for Bhojpuri language on Apple Silicon. This is a LoRA adapter on top of [`ai4bharat/indic-parler-tts`](https://huggingface.co/ai4bharat/indic-parler-tts). The base model supports 18 Indian languages — this adapter teaches it Bhojpuri phoneme patterns. ## Highlights - Runs **natively on Apple Silicon** (M1/M2/M3/M4) via [MLX](https://github.com/ml-explore/mlx) - **First Parler TTS port to MLX** — no PyTorch required - Fine-tuned on the [IISc SYSPIN Bhojpuri corpus](https://spiredatasets.ee.iisc.ac.in/syspincorpus) (CC-BY-4.0) - LoRA rank-8 adapter — only 4.3M trainable params out of 920M total (0.47%) - All 69 base model speakers can now speak Bhojpuri ## Model Details | Property | Value | |---|---| | Base model | `ai4bharat/indic-parler-tts` | | Training data | IISc SYSPIN Bhojpuri Female (5,537 clips) | | LoRA rank | 8, alpha 16 | | LoRA targets | Decoder self-attn, cross-attn Q/V, FFN | | Trained on | MacBook Pro (Apple Silicon) | | Framework | MLX | | Training steps | ~1,400 (2 epochs) | ## Audio Samples > **"ई बहुत नीमन बा। हम कल जाइब।"** — Bhojpuri (short) | | Base model | Fine-tuned | |---|---|---| | Divya |

| | Generic |

| > **"रउरा के राम राम। आज हम एही गाँव में रहीला। का हाल बा रउरा के?"** — Bhojpuri (long) | | Base model | Fine-tuned | |---|---|---| | Divya |

| | Generic |

| > **"नमस्ते, आप कैसे हैं? मैं बहुत अच्छा हूँ।"** — Hindi sanity check (should sound similar on both) | | Base model | Fine-tuned | |---|---|---| | Divya |

| | Generic |

| ## Usage ```bash pip install mlx mlx-lm soundfile ``` ```python import sys sys.path.insert(0, "path/to/mlx-audio-train") from models.indic_parler_tts.generate import load_model, generate from train.lora import apply_lora, load_adapters, LoRAConfig import soundfile as sf import mlx.core as mx from huggingface_hub import snapshot_download # 1. Load base model model, tokenizers = load_model("ai4bharat/indic-parler-tts") # 2. Apply LoRA and load adapter adapter_dir = snapshot_download("akashicmarga/indic-parler-tts-bhojpuri-lora") lora_config = LoRAConfig( rank=8, alpha=16.0, dropout=0.0, target_modules=[ "decoder.layers.*.self_attn.q", "decoder.layers.*.self_attn.k", "decoder.layers.*.self_attn.v", "decoder.layers.*.self_attn.out", "decoder.layers.*.cross_attn.q", "decoder.layers.*.cross_attn.v", "decoder.layers.*.fc1", "decoder.layers.*.fc2", ], model_type="indic_parler_tts", ) apply_lora(model, lora_config) load_adapters(model, f"{adapter_dir}/adapters.safetensors") mx.eval(model.parameters()) # 3. Generate Bhojpuri speech audio = generate( model, tokenizers, description="A female speaker delivers speech at a moderate pace. The recording is of very high quality.", text="रउरा के राम राम। आज हम एही गाँव में रहीला।", ) sf.write("bhojpuri.wav", audio, 44100) ``` Any speaker description supported by the base model works: ```python # Divya speaking Bhojpuri audio = generate( model, tokenizers, description="Divya's voice is slightly expressive and very animated. She speaks at a moderate pace.", text="ई बहुत नीमन बा। हम कल जाइब।", ) ``` ## Training Trained using [mlx-audio-train](https://github.com/akashicmarga/mlx-audio-train) on Apple Silicon. ```bash python scripts/train.py --config configs/indic_parler_bhojpuri.yaml ``` ## Dataset [IISc SYSPIN Corpus](https://spiredatasets.ee.iisc.ac.in/syspincorpus) — Bhojpuri Female Speaker License: CC-BY-4.0 ## License Adapter weights: Apache 2.0 Base model: Apache 2.0 (ai4bharat/indic-parler-tts) Training data: CC-BY-4.0 (IISc SYSPIN)