GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
saheedniyi
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
saheedniyi
Model Tree
HuggingFaceTB/SmolLM2-360M
Input Modalities
Output Modalities
Supported Functionality
YarnGPT2 is a text-to-speech (TTS) model designed to synthesize Nigerian-accented Languages (yoruba, igbo, hausa and english) leveraging pure language modelling without external adapters or complex architectures, offering high-quality, natural, and culturally relevant speech synthesis for diverse applications.
The model can generate audio on its own but its better to use a voice to prompt the model:
python
!git clone https://github.com/saheedniyi02/yarngpt.git pip install outetts uroman import osimport reimport jsonimport torchimport inflectimport randomimport uroman as urimport numpy as npimport torchaudioimport IPythonfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom outetts.wav_tokenizer.decoder import WavTokenizer !wget https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml!gdown 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt from yarngpt.audiotokenizer import AudioTokenizerV2 tokenizer_path="saheedniyi/YarnGPT2"wav_tokenizer_config_path="/content/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml"wav_tokenizer_model_path = "/content/wavtokenizer_large_speech_320_24k.ckpt" audio_tokenizer=AudioTokenizerV2( tokenizer_path,wav_tokenizer_model_path,wav_tokenizer_config_path ) model = AutoModelForCausalLM.from_pretrained(tokenizer_path,torch_dtype="auto").to(audio_tokenizer.device) #change the texttext="The election was won by businessman and politician, Moshood Abiola, but Babangida annulled the results, citing concerns over national security." # change the language and voiceprompt=audio_tokenizer.create_prompt(text,lang="english",speaker_name="idera") input_ids=audio_tokenizer.tokenize_prompt(prompt) output = model.generate( input_ids=input_ids, temperature=0.1, repetition_penalty=1.1, max_length=4000, #num_beams=5,# using a beam size helps for the local languages but not english ) codes=audio_tokenizer.get_codes(output)audio=audio_tokenizer.get_audio(codes)IPython.display.Audio(audio,rate=24000)torchaudio.save(f"Sample.wav", audio, sample_rate=24000)Generate Nigerian-accented English speech for experimental purposes.
The model is not suitable for generating speech in languages other than English or other accents.
The model may not capture the full diversity of Nigerian accents and could exhibit biases based on the training dataset. Also a lot of the text the model was trained on were automatically generated which could impact performance.
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. Feedback and diverse training data contributions are encouraged.
Listen to samples generated by YarnGPT:
Trained on a dataset of publicly available Nigerian movies, podcasts ( using the subtitle-audio pairs) and open source Nigerian-related audio data on Huggingface,
Audio files were preprocessed and resampled to 24Khz and tokenized using wavtokenizer.
python
@misc{yarngpt2025, author = {Saheed Azeez}, title = {YarnGPT: Nigerian-Accented English Text-to-Speech Model}, year = {2025}, publisher = {Hugging Face}, url = {https://huggingface.co/SaheedAzeez/yarngpt}}python
Saheed Azeez. (2025). YarnGPT: Nigerian-Accented English Text-to-Speech Model. Hugging Face. Available at: https://huggingface.co/saheedniyi/YarnGPT!git clone https://github.com/saheedniyi02/yarngpt.git pip install outetts uroman import osimport reimport jsonimport torchimport inflectimport randomimport uroman as urimport numpy as npimport torchaudioimport IPythonfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom outetts.wav_tokenizer.decoder import WavTokenizer !wget https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml!gdown 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt from yarngpt.audiotokenizer import AudioTokenizerV2 tokenizer_path="saheedniyi/YarnGPT2"wav_tokenizer_config_path="/content/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml"wav_tokenizer_model_path = "/content/wavtokenizer_large_speech_320_24k.ckpt" audio_tokenizer=AudioTokenizerV2( tokenizer_path,wav_tokenizer_model_path,wav_tokenizer_config_path ) model = AutoModelForCausalLM.from_pretrained(tokenizer_path,torch_dtype="auto").to(audio_tokenizer.device) #change the texttext="The election was won by businessman and politician, Moshood Abiola, but Babangida annulled the results, citing concerns over national security." # change the language and voiceprompt=audio_tokenizer.create_prompt(text,lang="english",speaker_name="idera") input_ids=audio_tokenizer.tokenize_prompt(prompt) output = model.generate( input_ids=input_ids, temperature=0.1, repetition_penalty=1.1, max_length=4000, #num_beams=5,# using a beam size helps for the local languages but not english ) codes=audio_tokenizer.get_codes(output)audio=audio_tokenizer.get_audio(codes)IPython.display.Audio(audio,rate=24000)torchaudio.save(f"Sample.wav", audio, sample_rate=24000)@misc{yarngpt2025, author = {Saheed Azeez}, title = {YarnGPT: Nigerian-Accented English Text-to-Speech Model}, year = {2025}, publisher = {Hugging Face}, url = {https://huggingface.co/SaheedAzeez/yarngpt}}Saheed Azeez. (2025). YarnGPT: Nigerian-Accented English Text-to-Speech Model. Hugging Face. Available at: https://huggingface.co/saheedniyi/YarnGPT