Downloads · 30 days
18
7% of all-time downloads
edzsaji26/orpheus-3b-0.1-hindi-male-lora
orpheus-3b-0.1-hindi-male-lora is a text-to-speech model from edzsaji26. Use it when you need text read aloud. The card lists the license as llama3.2.
A LoRA finetune of canopylabs/3b-hi-pretrain-researchrelease on the ai4bharat/Rasa Hindi Male subset, producing a single consistent male Hindi voice named arjun.
Downloads · 30 days
18
7% of all-time downloads
All-time downloads
241
Public
Parameters
3.8B
7.6 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors7.6 GB · 100%
From the Hugging Face model README
A LoRA finetune of canopylabs/3b-hi-pretrain-research_release on the ai4bharat/Rasa Hindi Male subset, producing a single consistent male Hindi voice named arjun.
| Base model | canopylabs/3b-hi-pretrain-research_release |
| Dataset | ai4bharat/Rasa — Hindi config, Male speaker |
| Train examples | 12,116 utterances (~23.78 hours) |
| Codec | SNAC 24kHz (hubertsiuzdak/snac_24khz) |
| LoRA rank | 32 (RSLoRA, α=64) |
| LoRA targets | All attention + MLP projections + lm_head + embed_tokens |
| Epochs | 3 |
| Batch size | 4 (effective, grad accum) |
| Learning rate | 2e-4 (cosine schedule) |
| Hardware | 1× NVIDIA A100-SXM4-40GB |
All samples generated with temperature=0.4, top_p=0.9, repetition_penalty=1.1.
नमस्ते, मेरा नाम अर्जुन है और मैं दिल्ली में रहता हूँ। मुझे हिंदी में बात करना बहुत पसंद है क्योंकि यह मेरी मातृभाषा है।
<audio controls> <source src="https://huggingface.co/edzsaji26/orpheus-3b-0.1-hindi-male-lora/resolve/main/audio/sample_0.wav" type="audio/wav"> </audio>आज सुबह से ही मौसम बहुत सुहाना है और आसमान में हल्के बादल छाए हुए हैं। ऐसे मौसम में चाय पीते हुए किताब पढ़ना बहुत अच्छा लगता है।
<audio controls> <source src="https://huggingface.co/edzsaji26/orpheus-3b-0.1-hindi-male-lora/resolve/main/audio/sample_1.wav" type="audio/wav"> </audio>भारत एक विविधताओं से भरा हुआ देश है जहाँ अलग-अलग भाषाएँ, संस्कृतियाँ और परंपराएँ एक साथ फलती-फूलती हैं। यहाँ के लोग मिलजुल कर रहते हैं और एक-दूसरे की मदद करते हैं।
<audio controls> <source src="https://huggingface.co/edzsaji26/orpheus-3b-0.1-hindi-male-lora/resolve/main/audio/sample_2.wav" type="audio/wav"> </audio>import torch
import wave
import numpy as np
from snac import SNAC
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_ID = "edzsaji26/orpheus-3b-0.1-hindi-male-lora"
VOICE_NAME = "arjun"
AUDIO_OFFSET = 128266
STOP_TOKEN = 128258
SAMPLE_RATE = 24_000
device = "cuda" if torch.cuda.is_available() else "cpu"
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto")
model.eval()
snac = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval().to(device)
def synthesise(text):
prompt = f"{VOICE_NAME}: {text}"
ids = tokenizer(prompt, return_tensors="pt").input_ids
input_ids = torch.cat([
torch.tensor([[128259]]),
ids,
torch.tensor([[128009, 128260, 128261, 128257]])
], dim=1).to(device)
with torch.inference_mode():
out = model.generate(
input_ids=input_ids,
max_new_tokens=2000,
do_sample=True,
temperature=0.4,
top_p=0.9,
repetition_penalty=1.1,
eos_token_id=STOP_TOKEN,
)
new_tokens = out[0, input_ids.shape[1]:].tolist()
audio_tokens = [t for t in new_tokens if t != STOP_TOKEN]
n_frames = len(audio_tokens) // 7
audio_tokens = audio_tokens[:n_frames * 7]
c0, c1, c2 = [], [], []
for f in range(n_frames):
i = f * 7
c0.append(audio_tokens[i] - AUDIO_OFFSET)
c1.append(audio_tokens[i+1] - AUDIO_OFFSET - 4096)
c2.append(audio_tokens[i+2] - AUDIO_OFFSET - 2*4096)
c2.append(audio_tokens[i+3] - AUDIO_OFFSET - 3*4096)
c1.append(audio_tokens[i+4] - AUDIO_OFFSET - 4*4096)
c2.append(audio_tokens[i+5] - AUDIO_OFFSET - 5*4096)
c2.append(audio_tokens[i+6] - AUDIO_OFFSET - 6*4096)
codes = [torch.tensor(c0).unsqueeze(0).to(device),
torch.tensor(c1).unsqueeze(0).to(device),
torch.tensor(c2).unsqueeze(0).to(device)]
with torch.inference_mode():
audio = snac.decode(codes)
waveform = audio.squeeze().cpu().numpy()
int16 = (waveform * 32767).clip(-32768, 32767).astype(np.int16)
with wave.open("output.wav", "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2)
wf.setframerate(SAMPLE_RATE)
wf.writeframes(int16.tobytes())
synthesise("नमस्ते, मेरा नाम अर्जुन है और मैं आपसे बात करके बहुत खुश हूँ।")
arjun: <hindi text here>
The voice name arjun is the learned speaker identity — always include it as the prefix.
If you use this model, please also cite the underlying work:
@misc{orpheus2025,
title = {Orpheus TTS},
author = {Canopy Labs},
year = {2025},
url = {https://github.com/canopyai/Orpheus-TTS}
}
@inproceedings{ai4bharat2024rasa,
author = {Praveen Srinivasa Varadhan and Ashwin Sankar and Giri Raju and Mitesh M. Khapra},
title = {Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings},
booktitle = {Proc. INTERSPEECH 2024},
year = {2024}
}