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 AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("openai/whisper-large-v2") model = PeftModel.from_pretrained(base_model, "MALIBA-AI/songhoy-asr") - Notebooks
- Google Colab
- Kaggle
Update adapter_config.json
Browse files- adapter_config.json +1 -1
adapter_config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"q_proj",
|
| 31 |
"v_proj"
|
| 32 |
],
|
| 33 |
-
"task_type":
|
| 34 |
"use_dora": false,
|
| 35 |
"use_rslora": false
|
| 36 |
}
|
|
|
|
| 30 |
"q_proj",
|
| 31 |
"v_proj"
|
| 32 |
],
|
| 33 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 34 |
"use_dora": false,
|
| 35 |
"use_rslora": false
|
| 36 |
}
|