Automatic Speech Recognition
Transformers
Safetensors
GGUF
whisper
speech
audio
asr
fine-tuned
naija
nigerian
african-languages
transcribe.cpp
Instructions to use amn-raw/naijaVox2_quantized_int8_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amn-raw/naijaVox2_quantized_int8_gguf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="amn-raw/naijaVox2_quantized_int8_gguf")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("amn-raw/naijaVox2_quantized_int8_gguf") model = AutoModelForSpeechSeq2Seq.from_pretrained("amn-raw/naijaVox2_quantized_int8_gguf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "feature_extractor": { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| }, | |
| "processor_class": "WhisperProcessor", | |
| "n_fft": 400, | |
| "chunk_length": 30, | |
| "feature_size": 128, | |
| "sampling_rate": 16000, | |
| "hop_length": 160, | |
| "n_mels": 128 | |
| } |