GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
snorbyte
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
snorbyte
Model Tree
snorbyte/snorTTS-Indic-v0
Input Modalities
Output Modalities
Supported Functionality
| Item | Details |
|---|---|
| Architecture | LLaMA-3.2-3B |
| Base model | canopylabs/3b-hi-pretrain-research_release |
| Audio codec | SNAC @ 24 kHz, 3 codebooks (12,288 new tokens) |
| Languages | Hindi, Gujarati, Marathi, Punjabi, Bengali, Telugu, Kannada, Malayalam, Tamil |
For details about the training and dataset, please refer to Train a SoTA Multilingual Indic Text-to-Speech (TTS).
You can find the training script (train_orepheus.py) in this repository. It is a single, self-contained script for fine-tuning the base model.
👉 Dataset used for training: snorbyte/indic-tts-sample-snac-encoded
👉 To host in Modal: Check the modal folder
bash
sudo apt updatebash
sudo apt install -y sox libsox-dev bash
pip uninstall -y torch torchaudio bash
pip install unsloth loguru snac deepfilternet pydub soundfile librosa torchaudiopython
from unsloth import FastLanguageModelfrom snac import SNACimport soundfile as sfimport numpy as npfrom loguru import loggerfrom df.enhance import init_df, enhance, save_audioimport torchimport librosaimport torchaudioimport os #Name of the modelMODEL_NAME = 'snorbyte/snorTTS-Indic-v0'MAX_SEQ_LENGTH = 4096HUGGINGFACE_TOKEN = "" # ! Add your hugging face token # Load the model and tokenizer.model, tokenizer = FastLanguageModel.from_pretrained( model_name=MODEL_NAME, # load_in_4bit=True, max_seq_length=MAX_SEQ_LENGTH, token=HUGGINGFACE_TOKEN,)logger.success(f"Loaded model: {MODEL_NAME}") # Load the end of speech token for the tokenizer.tokeniser_length = 128256end_of_speech_id = tokeniser_length + 2pad_token_id = tokeniser_length + 7audio_start_id = tokeniser_length + 10 pad_token = tokenizer.decode([pad_token_id])logger.success("Load special tokens for the tokenizer.") # Wrap Model for InferenceFastLanguageModel.for_inference(model)logger.success(f"{MODEL_NAME} is ready for inference.") # Set the padding token and padding side.tokenizer.pad_token = pad_tokentokenizer.padding_side = "left"logger.success("Set padding token and padding side for the tokenizer.") # Load the SNAC model for audio decoding.snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")logger.success("Loaded SNAC model for audio decoding.") # Load DeepFilter for optional post processingdf_model, df_state, _ = init_df() # Function to generate audiodef generate_audio( row, model, tokenizer, user=False, temperature=0.4, top_p=0.9, repetition_penalty=1.05): try: if user: prompt = row["eval_text_user"] else: prompt = row["eval_text_no_user"] inputs = tokenizer(prompt, add_special_tokens=False, return_tensors="pt") max_tokens = MAX_SEQ_LENGTH - inputs.input_ids.shape[1] output = model.generate( input_ids=inputs.input_ids.to("cuda"), attention_mask=inputs.attention_mask.to("cuda"), max_new_tokens=max_tokens, temperature=temperature, top_p=top_p, repetition_penalty=repetition_penalty, eos_token_id=end_of_speech_id, ) audio_ids = [] for id in output[0]: if id >= audio_start_id: audio_ids.append(id.item()) clean_audio_ids = [] for i in range((len(audio_ids) + 1) // 7): for j in range(7): clean_audio_ids += [audio_ids[7 * i + j] - audio_start_id] codes = [[], [], []] for i in range((len(clean_audio_ids) + 1) // 7): codes[0].append(clean_audio_ids[7 * i]) codes[1].append(clean_audio_ids[7 * i + 1] - 4096) codes[2].append(clean_audio_ids[7 * i + 2] - (2 * 4096)) codes[2].append(clean_audio_ids[7 * i + 3] - (3 * 4096)) codes[1].append(clean_audio_ids[7 * i + 4] - (4 * 4096)) codes[2].append(clean_audio_ids[7 * i + 5] - (5 * 4096)) codes[2].append(clean_audio_ids[7 * i + 6] - (6 * 4096)) codes = [ torch.tensor(codes[0]).unsqueeze(0), torch.tensor(codes[1]).unsqueeze(0), torch.tensor(codes[2]).unsqueeze(0), ] try: audio = snac_model.decode(codes) except Exception as e: logger.error(f"Error decoding audio: {e}") return None return audio.detach().squeeze().to("cpu").numpy() except Exception as e: logger.error(f"Error decoding audio: {e}") return None # Run inference.# * Please refer to the training script to create prompt from SNAC tokens.row = { "eval_text_user": f"<custom_token_3><|begin_of_text|>kannada142: ಅಯ್ಯಯ್ಯೋ... Whitefield ಗೆ reach ಆಗೋಕೆ almost 10 hours ಆಯ್ತು you know... traffic was so terrible today <|eot_id|><custom_token_4><custom_token_5><custom_token_1>" } eval_sample = generate_audio(row, model, tokenizer, True)if eval_sample is None: logger.error("Failed to generate audio for evaluation sample.")else: logger.success("Audio Generated. Post Processing Started") ## post-processing settings filename = "eval.wav" speed = 1.05 #add speed up according to speaker denoise = False #denoise if you want output = eval_sample.astype(np.float32) #speed up if abs(speed - 1.0) > 1e-4: output_t = torch.from_numpy(output).unsqueeze(0) output_speed, _ = torchaudio.sox_effects.apply_effects_tensor(output_t, 24_000, effects=[["tempo", f"{speed}"]]) output = output_speed.squeeze(0).cpu().numpy() #denoise if denoise: resampled_48k = librosa.resample(output, orig_sr=24_000, target_sr=48_000) resampled_48k = torch.from_numpy(resampled_48k).unsqueeze(0) output_48k = enhance(df_model, df_state, resampled_48k) output_48k = output_48k.squeeze(0).cpu().numpy() output = librosa.resample(output_48k, orig_sr=48_000, target_sr=24_000) logger.success("Saving Final Output...") #save sf.write(filename, output, 24_000) logger.success(f"Generated and saved evaluation sample audio as {filename}.")python
{ "eval_text_no_user": f"<custom_token_3><|begin_of_text|>{utterance}<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}python
{ "eval_text_no_user": f"<custom_token_3><|begin_of_text|>நிச்சயமா. ரோம் ல் இரவு நேரம் ரொம்ப அழகா இருக்கு—piazzaகள் சுத்துறதுக்கு நல்ல நேரம்.<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"},python
{ "eval_text_user": f"<custom_token_3><|begin_of_text|>{language}{speaker_id}: {utterance}<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}📝
utterancecan be in native language of the speaker, multi-lingual, or code-switched as well.
python
{ "eval_text_user": f"<custom_token_3><|begin_of_text|>hindi159: चलते रहो इस सफर में बिना रुके, क्योंकि मंज़िलें खुद राह दिखाने लगती हैं <|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}python
{ "eval_text_user": f"<custom_token_3><|begin_of_text|>bengali125: मुझे तो लगा वो आएगा, ஆனா அவன் வந்து full drama பண்ணிட்டான், আর শেষে আবার আমাকে দোষ দিচ্ছে <|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}| Language | Speakers | Recommended Speedup |
|---|---|---|
| Hindi | [159,49,43] | [1.05,1.1,1.1] |
| Tamil | [188,128,176] | [1.1,1.15,1.1] |
| Bengali | [125] | [1.1] |
| Malayalam | [189,124] | [1.1,1.1] |
| Kannada | [142,138,131,59] | [1.05,1.1,1.1,1.1] |
| Telugu | [69,133] | [1.1,1.1] |
| Punjabi | [191,67,201] | [1.08,1.06,1.1] |
| Gujarati | [62,190] | [1.15,1.25] |
| Marathi | [205,82,199,203] | [1.05,1.05,1.1,1.15] |
👉 Mail: founders@snorbyte.com
👉 Website: https://snorbyte.com
BibTeX:
bibtex
@misc{indictextaudio2025, title={snorTTS-Indic-v0: Multilingual Indic TTS}, author={snorbyte}, year={2025}, howpublished={\url{snorbyte/snorTTS-Indic-v0}}, note={Apache-2.0}}sudo apt install -y sox libsox-dev pip install unsloth loguru snac deepfilternet pydub soundfile librosa torchaudiofrom unsloth import FastLanguageModelfrom snac import SNACimport soundfile as sfimport numpy as npfrom loguru import loggerfrom df.enhance import init_df, enhance, save_audioimport torchimport librosaimport torchaudioimport os #Name of the modelMODEL_NAME = 'snorbyte/snorTTS-Indic-v0'MAX_SEQ_LENGTH = 4096HUGGINGFACE_TOKEN = "" # ! Add your hugging face token # Load the model and tokenizer.model, tokenizer = FastLanguageModel.from_pretrained( model_name=MODEL_NAME, # load_in_4bit=True, max_seq_length=MAX_SEQ_LENGTH, token=HUGGINGFACE_TOKEN,)logger.success(f"Loaded model: {MODEL_NAME}") # Load the end of speech token for the tokenizer.tokeniser_length = 128256end_of_speech_id = tokeniser_length + 2pad_token_id = tokeniser_length + 7audio_start_id = tokeniser_length + 10 pad_token = tokenizer.decode([pad_token_id])logger.success("Load special tokens for the tokenizer.") # Wrap Model for InferenceFastLanguageModel.for_inference(model)logger.success(f"{MODEL_NAME} is ready for inference.") # Set the padding token and padding side.tokenizer.pad_token = pad_tokentokenizer.padding_side = "left"logger.success("Set padding token and padding side for the tokenizer.") # Load the SNAC model for audio decoding.snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")logger.success("Loaded SNAC model for audio decoding.") # Load DeepFilter for optional post processingdf_model, df_state, _ = init_df() # Function to generate audiodef generate_audio( row, model, tokenizer, user=False, temperature=0.4, top_p=0.9, repetition_penalty=1.05): try: if user: prompt = row["eval_text_user"] else: prompt = row["eval_text_no_user"] inputs = tokenizer(prompt, add_special_tokens=False, return_tensors="pt") max_tokens = MAX_SEQ_LENGTH - inputs.input_ids.shape[1] output = model.generate( input_ids=inputs.input_ids.to("cuda"), attention_mask=inputs.attention_mask.to("cuda"), max_new_tokens=max_tokens, temperature=temperature, top_p=top_p, repetition_penalty=repetition_penalty, eos_token_id=end_of_speech_id, ) audio_ids = [] for id in output[0]: if id >= audio_start_id: audio_ids.append(id.item()) clean_audio_ids = [] for i in range((len(audio_ids) + 1) // 7): for j in range(7): clean_audio_ids += [audio_ids[7 * i + j] - audio_start_id] codes = [[], [], []] for i in range((len(clean_audio_ids) + 1) // 7): codes[0].append(clean_audio_ids[7 * i]) codes[1].append(clean_audio_ids[7 * i + 1] - 4096) codes[2].append(clean_audio_ids[7 * i + 2] - (2 * 4096)) codes[2].append(clean_audio_ids[7 * i + 3] - (3 * 4096)) codes[1].append(clean_audio_ids[7 * i + 4] - (4 * 4096)) codes[2].append(clean_audio_ids[7 * i + 5] - (5 * 4096)) codes[2].append(clean_audio_ids[7 * i + 6] - (6 * 4096)) codes = [ torch.tensor(codes[0]).unsqueeze(0), torch.tensor(codes[1]).unsqueeze(0), torch.tensor(codes[2]).unsqueeze(0), ] try: audio = snac_model.decode(codes) except Exception as e: logger.error(f"Error decoding audio: {e}") return None return audio.detach().squeeze().to("cpu").numpy() except Exception as e: logger.error(f"Error decoding audio: {e}") return None # Run inference.# * Please refer to the training script to create prompt from SNAC tokens.row = { "eval_text_user": f"<custom_token_3><|begin_of_text|>kannada142: ಅಯ್ಯಯ್ಯೋ... Whitefield ಗೆ reach ಆಗೋಕೆ almost 10 hours ಆಯ್ತು you know... traffic was so terrible today <|eot_id|><custom_token_4><custom_token_5><custom_token_1>" } eval_sample = generate_audio(row, model, tokenizer, True)if eval_sample is None: logger.error("Failed to generate audio for evaluation sample.")else: logger.success("Audio Generated. Post Processing Started") ## post-processing settings filename = "eval.wav" speed = 1.05 #add speed up according to speaker denoise = False #denoise if you want output = eval_sample.astype(np.float32) #speed up if abs(speed - 1.0) > 1e-4: output_t = torch.from_numpy(output).unsqueeze(0) output_speed, _ = torchaudio.sox_effects.apply_effects_tensor(output_t, 24_000, effects=[["tempo", f"{speed}"]]) output = output_speed.squeeze(0).cpu().numpy() #denoise if denoise: resampled_48k = librosa.resample(output, orig_sr=24_000, target_sr=48_000) resampled_48k = torch.from_numpy(resampled_48k).unsqueeze(0) output_48k = enhance(df_model, df_state, resampled_48k) output_48k = output_48k.squeeze(0).cpu().numpy() output = librosa.resample(output_48k, orig_sr=48_000, target_sr=24_000) logger.success("Saving Final Output...") #save sf.write(filename, output, 24_000) logger.success(f"Generated and saved evaluation sample audio as {filename}."){ "eval_text_no_user": f"<custom_token_3><|begin_of_text|>{utterance}<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}{ "eval_text_no_user": f"<custom_token_3><|begin_of_text|>நிச்சயமா. ரோம் ல் இரவு நேரம் ரொம்ப அழகா இருக்கு—piazzaகள் சுத்துறதுக்கு நல்ல நேரம்.<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"},{ "eval_text_user": f"<custom_token_3><|begin_of_text|>{language}{speaker_id}: {utterance}<|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}{ "eval_text_user": f"<custom_token_3><|begin_of_text|>hindi159: चलते रहो इस सफर में बिना रुके, क्योंकि मंज़िलें खुद राह दिखाने लगती हैं <|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}{ "eval_text_user": f"<custom_token_3><|begin_of_text|>bengali125: मुझे तो लगा वो आएगा, ஆனா அவன் வந்து full drama பண்ணிட்டான், আর শেষে আবার আমাকে দোষ দিচ্ছে <|eot_id|><custom_token_4><custom_token_5><custom_token_1>"}@misc{indictextaudio2025, title={snorTTS-Indic-v0: Multilingual Indic TTS}, author={snorbyte}, year={2025}, howpublished={\url{snorbyte/snorTTS-Indic-v0}}, note={Apache-2.0}}