GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
salihfurkaan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
salihfurkaan
Model Tree
unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
py
!pip install transformersfrom transformers import pipelinepipe = pipeline("text-to-speech", model="salihfurkaan/VoxPolska-V1-Merged-16bit")py
!pip install snac torch transformers import torch import snac from snac import SNAC from transformers import AutoTokenizer, AutoModelForCausalLM import os from IPython.display import display, Audio device = torch.device("cuda" if torch.cuda.is_available() else "cpu") tokenizer = AutoTokenizer.from_pretrained("salihfurkaan/VoxPolska-V1-Merged-16bit") model = AutoModelForCausalLM.from_pretrained("salihfurkaan/VoxPolska-V1-Merged-16bit").to(device) os.environ["HF_TOKEN"] = "your huggingface token here" snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").to(device) prompts = [ "Cześć, jestem dużym modelem języka sztucznej inteligencji" ] #an example prompt chosen_voice = None prompts_ = [(f"{chosen_voice}: " + p) if chosen_voice else p for p in prompts] all_input_ids = [] for prompt in prompts_: input_ids = tokenizer(prompt, return_tensors="pt").input_ids all_input_ids.append(input_ids) start_token = torch.tensor([[128259]], dtype=torch.int64) # Start of human end_tokens = torch.tensor([[128009, 128260]], dtype=torch.int64) # End of text, End of human all_modified_input_ids = [] for input_ids in all_input_ids: modified_input_ids = torch.cat([start_token, input_ids, end_tokens], dim=1) all_modified_input_ids.append(modified_input_ids) all_padded_tensors = [] all_attention_masks = [] max_length = max([x.shape[1] for x in all_modified_input_ids]) for modified_input_ids in all_modified_input_ids: padding = max_length - modified_input_ids.shape[1] padded_tensor = torch.cat([torch.full((1, padding), 128263, dtype=torch.int64), modified_input_ids], dim=1) attention_mask = torch.cat([torch.zeros((1, padding), dtype=torch.int64), torch.ones((1, modified_input_ids.shape[1]), dtype=torch.int64)], dim=1) all_padded_tensors.append(padded_tensor) all_attention_masks.append(attention_mask) all_padded_tensors = torch.cat(all_padded_tensors, dim=0).to(device) all_attention_masks = torch.cat(all_attention_masks, dim=0).to(device) generated_ids = model.generate( input_ids=all_padded_tensors, attention_mask=all_attention_masks, max_new_tokens=1200, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.1, num_return_sequences=1, eos_token_id=128258, use_cache=True ) token_to_find = 128257 token_to_remove = 128258 token_indices = (generated_ids == token_to_find).nonzero(as_tuple=True) if len(token_indices[1]) > 0: last_occurrence_idx = token_indices[1][-1].item() cropped_tensor = generated_ids[:, last_occurrence_idx+1:] else: cropped_tensor = generated_ids processed_rows = [] for row in cropped_tensor: masked_row = row[row != token_to_remove] processed_rows.append(masked_row) code_lists = [] for row in processed_rows: row_length = row.size(0) new_length = (row_length // 7) * 7 trimmed_row = row[:new_length] trimmed_row = [t - 128266 for t in trimmed_row] code_lists.append(trimmed_row) def redistribute_codes(code_list): layer_1 = [] layer_2 = [] layer_3 = [] for i in range((len(code_list) + 1) // 7): layer_1.append(code_list[7 * i]) layer_2.append(code_list[7 * i + 1] - 4096) layer_3.append(code_list[7 * i + 2] - (2 * 4096)) layer_3.append(code_list[7 * i + 3] - (3 * 4096)) layer_2.append(code_list[7 * i + 4] - (4 * 4096)) layer_3.append(code_list[7 * i + 5] - (5 * 4096)) layer_3.append(code_list[7 * i + 6] - (6 * 4096)) codes = [ torch.tensor(layer_1).unsqueeze(0).to(device), torch.tensor(layer_2).unsqueeze(0).to(device), torch.tensor(layer_3).unsqueeze(0).to(device) ] audio_hat = snac_model.decode(codes) return audio_hat my_samples = [] for code_list in code_lists: samples = redistribute_codes(code_list) my_samples.append(samples) if len(prompts) != len(my_samples): raise Exception("Number of prompts and samples do not match") else: for i in range(len(my_samples)): print(prompts[i]) samples = my_samples[i] display(Audio(samples.detach().squeeze().to("cpu").numpy(), rate=24000)) del my_samples, samplesYou can get your huggingface token from here
For questions, suggestions, and feedback, please open an issue on HuggingFace. You can also reach the author via: LinkedIn
Do not use this model for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By using this model, you agree to follow all applicable laws and ethical guidelines.
none
@misc{ title={salihfurkaan/VoxPolska-V1-Merged-16bit}, author={Salih Furkan Erik}, year={2025}, url={https://huggingface.co/salihfurkaan/VoxPolska-V1-Merged-16bit/}}!pip install transformersfrom transformers import pipelinepipe = pipeline("text-to-speech", model="salihfurkaan/VoxPolska-V1-Merged-16bit") !pip install snac torch transformers import torch import snac from snac import SNAC from transformers import AutoTokenizer, AutoModelForCausalLM import os from IPython.display import display, Audio device = torch.device("cuda" if torch.cuda.is_available() else "cpu") tokenizer = AutoTokenizer.from_pretrained("salihfurkaan/VoxPolska-V1-Merged-16bit") model = AutoModelForCausalLM.from_pretrained("salihfurkaan/VoxPolska-V1-Merged-16bit").to(device) os.environ["HF_TOKEN"] = "your huggingface token here" snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").to(device) prompts = [ "Cześć, jestem dużym modelem języka sztucznej inteligencji" ] #an example prompt chosen_voice = None prompts_ = [(f"{chosen_voice}: " + p) if chosen_voice else p for p in prompts] all_input_ids = [] for prompt in prompts_: input_ids = tokenizer(prompt, return_tensors="pt").input_ids all_input_ids.append(input_ids) start_token = torch.tensor([[128259]], dtype=torch.int64) # Start of human end_tokens = torch.tensor([[128009, 128260]], dtype=torch.int64) # End of text, End of human all_modified_input_ids = [] for input_ids in all_input_ids: modified_input_ids = torch.cat([start_token, input_ids, end_tokens], dim=1) all_modified_input_ids.append(modified_input_ids) all_padded_tensors = [] all_attention_masks = [] max_length = max([x.shape[1] for x in all_modified_input_ids]) for modified_input_ids in all_modified_input_ids: padding = max_length - modified_input_ids.shape[1] padded_tensor = torch.cat([torch.full((1, padding), 128263, dtype=torch.int64), modified_input_ids], dim=1) attention_mask = torch.cat([torch.zeros((1, padding), dtype=torch.int64), torch.ones((1, modified_input_ids.shape[1]), dtype=torch.int64)], dim=1) all_padded_tensors.append(padded_tensor) all_attention_masks.append(attention_mask) all_padded_tensors = torch.cat(all_padded_tensors, dim=0).to(device) all_attention_masks = torch.cat(all_attention_masks, dim=0).to(device) generated_ids = model.generate( input_ids=all_padded_tensors, attention_mask=all_attention_masks, max_new_tokens=1200, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.1, num_return_sequences=1, eos_token_id=128258, use_cache=True ) token_to_find = 128257 token_to_remove = 128258 token_indices = (generated_ids == token_to_find).nonzero(as_tuple=True) if len(token_indices[1]) > 0: last_occurrence_idx = token_indices[1][-1].item() cropped_tensor = generated_ids[:, last_occurrence_idx+1:] else: cropped_tensor = generated_ids processed_rows = [] for row in cropped_tensor: masked_row = row[row != token_to_remove] processed_rows.append(masked_row) code_lists = [] for row in processed_rows: row_length = row.size(0) new_length = (row_length // 7) * 7 trimmed_row = row[:new_length] trimmed_row = [t - 128266 for t in trimmed_row] code_lists.append(trimmed_row) def redistribute_codes(code_list): layer_1 = [] layer_2 = [] layer_3 = [] for i in range((len(code_list) + 1) // 7): layer_1.append(code_list[7 * i]) layer_2.append(code_list[7 * i + 1] - 4096) layer_3.append(code_list[7 * i + 2] - (2 * 4096)) layer_3.append(code_list[7 * i + 3] - (3 * 4096)) layer_2.append(code_list[7 * i + 4] - (4 * 4096)) layer_3.append(code_list[7 * i + 5] - (5 * 4096)) layer_3.append(code_list[7 * i + 6] - (6 * 4096)) codes = [ torch.tensor(layer_1).unsqueeze(0).to(device), torch.tensor(layer_2).unsqueeze(0).to(device), torch.tensor(layer_3).unsqueeze(0).to(device) ] audio_hat = snac_model.decode(codes) return audio_hat my_samples = [] for code_list in code_lists: samples = redistribute_codes(code_list) my_samples.append(samples) if len(prompts) != len(my_samples): raise Exception("Number of prompts and samples do not match") else: for i in range(len(my_samples)): print(prompts[i]) samples = my_samples[i] display(Audio(samples.detach().squeeze().to("cpu").numpy(), rate=24000)) del my_samples, samples@misc{ title={salihfurkaan/VoxPolska-V1-Merged-16bit}, author={Salih Furkan Erik}, year={2025}, url={https://huggingface.co/salihfurkaan/VoxPolska-V1-Merged-16bit/}}