Automatic Speech Recognition
PEFT
Safetensors
Xiang Chinese
French
whisper
asr
songhoy
Mali
MALIBA-AI
lora
fine-tuned
code-switching
african-language
Eval Results (legacy)
Instructions to use MALIBA-AI/songhoy-asr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MALIBA-AI/songhoy-asr with PEFT:
from peft import PeftModel from transformers import AutoModelForSpeechSeq2Seq base_model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v2") model = PeftModel.from_pretrained(base_model, "MALIBA-AI/songhoy-asr") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from MALIBA-AI/songhoy-asr: direct link, hf CLI and curl.
- Browser
- Download file 356 Bytes
-
https://huggingface.co/MALIBA-AI/songhoy-asr/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://MALIBA-AI/songhoy-asr/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/MALIBA-AI/songhoy-asr/resolve/main/preprocessor_config.json
356 Bytes
| { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |