GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
namphungdn134
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
namphungdn134
Model Tree
openai/whisper-base
Input Modalities
Output Modalities
Supported Functionality
This is a fine-tuned version of openai/whisper-base model on 100 hours of Vietnamese speech data. The model aims to improve transcription accuracy and robustness for Vietnamese automatic speech recognition (ASR) tasks, especially in real-world scenarios.
Evaluation was performed on a held-out test set with diverse regional accents and speaking styles.
The Whisper Base model is a transformer-based sequence-to-sequence model designed for automatic speech recognition and translation tasks. It has been trained on over 680,000 hours of labeled audio data in multiple languages. The fine-tuned version of this model focuses on the Vietnamese language, aiming to improve transcription accuracy and handling of local dialects.
This model works with the WhisperProcessor to pre-process audio inputs into log-Mel spectrograms and decode them into text.
To use the fine-tuned model, you can go to: https://github.com/namphung134/np-asr-vietnamese
Or you can follow these steps:
Install the required dependencies:
python
# Install required libraries!pip install transformers torch librosa soundfile --quiet # Import necessary librariesimport torchimport librosaimport soundfile as sffrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline print("Environment setup completed!")Use the model for inference:
python
import torchimport librosafrom transformers import AutoProcessor, AutoModelForSpeechSeq2Seq device = "cuda" if torch.cuda.is_available() else "cpu"print(f"Using device: {device}") # Load processor and modelmodel_id = "namphungdn134/whisper-base-vi"print(f"Loading model from: {model_id}")processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device) # config language and taskforced_decoder_ids = processor.get_decoder_prompt_ids(language="vi", task="transcribe")model.config.forced_decoder_ids = forced_decoder_idsprint(f"Forced decoder IDs for Vietnamese: {forced_decoder_ids}") # Preprocessaudio_path = "example.wav" print(f"Loading audio from: {audio_path}")audio, sr = librosa.load(audio_path, sr=16000) input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(device)print(f"Input features shape: {input_features.shape}") # Generateprint("Generating transcription...")with torch.no_grad(): predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print("📝 Transcription:", transcription) # Debug: Print token to checkprint("Predicted IDs:", predicted_ids[0].tolist())This model is licensed under the MIT License.
If you use this model in your research or application, please cite the original Whisper model and this fine-tuning work as follows:
text
@article{Whisper2021, title={Whisper: A Multilingual Speech Recognition Model}, author={OpenAI}, year={2021}, journal={arXiv:2202.12064}, url={https://arxiv.org/abs/2202.12064}}text
@misc{title={Whisper Base Vi V1.1 - Nam Phung}, author={Nam Phùng}, organization={DUT}, year={2025}, url={https://huggingface.co/namphungdn134/whisper-base-vi}}For questions, collaborations, or suggestions, feel free to reach out via [namphungdn134@gmail.com].
# Install required libraries!pip install transformers torch librosa soundfile --quiet # Import necessary librariesimport torchimport librosaimport soundfile as sffrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline print("Environment setup completed!")import torchimport librosafrom transformers import AutoProcessor, AutoModelForSpeechSeq2Seq device = "cuda" if torch.cuda.is_available() else "cpu"print(f"Using device: {device}") # Load processor and modelmodel_id = "namphungdn134/whisper-base-vi"print(f"Loading model from: {model_id}")processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device) # config language and taskforced_decoder_ids = processor.get_decoder_prompt_ids(language="vi", task="transcribe")model.config.forced_decoder_ids = forced_decoder_idsprint(f"Forced decoder IDs for Vietnamese: {forced_decoder_ids}") # Preprocessaudio_path = "example.wav" print(f"Loading audio from: {audio_path}")audio, sr = librosa.load(audio_path, sr=16000) input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(device)print(f"Input features shape: {input_features.shape}") # Generateprint("Generating transcription...")with torch.no_grad(): predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print("📝 Transcription:", transcription) # Debug: Print token to checkprint("Predicted IDs:", predicted_ids[0].tolist())@article{Whisper2021, title={Whisper: A Multilingual Speech Recognition Model}, author={OpenAI}, year={2021}, journal={arXiv:2202.12064}, url={https://arxiv.org/abs/2202.12064}}@misc{title={Whisper Base Vi V1.1 - Nam Phung}, author={Nam Phùng}, organization={DUT}, year={2025}, url={https://huggingface.co/namphungdn134/whisper-base-vi}}