Indic Parler Tts Nepali Finetuned Dgx v2.2 Cosine

--- language: - ne library_name: parler-tts tags: - text-to-speech - nepali - parler-tts - finetuned --- # Nepali Parler-TTS -- Finetuned Nepali finetuned version of [Indic Parler-TTS](ai4bharat/indic-parler-tts-pretrained). ## Training config | Parameter | Value | |---|---| | Base model | `ai4bharat/indic-parler-tts-pretrained` | | Resumed from | `N/A` | | GPU | DGX | | Epochs | 2 | | Batch size | 32 | | Grad accum steps | 2 | | Effective batch size | 64 | | Learning rate | 3e-06 | | LR schedule | cosine with warmup | | Warmup steps | 208.0 | | Total steps | 2080 | | Max audio tokens | 550 | | Precision | bfloat16 | | Grad clip norm | 1.0 | ## Results | Metric | Value | |---|---| | Best val loss | 6.7131 | | Steps trained | 2080 | | Training time | 1242.3 min | ## Usage ```python from parler_tts import ParlerTTSForConditionalGeneration from transformers import AutoTokenizer import torch, soundfile as sf model_id = "milanakdj/indic-parler-tts-nepali-finetuned-dgx-v2.2-cosine" device = "cuda" if torch.cuda.is_available() else "cpu" model = ParlerTTSForConditionalGeneration.from_pretrained(model_id).to(device) prompt_tokenizer = AutoTokenizer.from_pretrained(model_id) desc_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path) prompt = "नमस्ते, तपाईंलाई कस्तो छ?" description = "Shristi speaks clearly in Nepali at a steady pace. Very high quality audio." desc_enc = desc_tokenizer(description, return_tensors="pt").to(device) prompt_enc = prompt_tokenizer(prompt, return_tensors="pt").to(device) with torch.inference_mode(): gen = model.generate( input_ids=desc_enc.input_ids, attention_mask=desc_enc.attention_mask, prompt_input_ids=prompt_enc.input_ids, prompt_attention_mask=prompt_enc.attention_mask, ) sf.write("out.wav", gen.cpu().numpy().squeeze(), model.config.sampling_rate) ```

Source context: 3 downloads · 0 likes · Pipeline text-to-speech · Library parler-tts · Repo milanakdj/indic-parler-tts-nepali-finetuned-dgx-v2.2-cosine