Upload README.md with huggingface_hub

README.md

@@ -2175,10 +2175,10 @@ extractor = sherpa_onnx.SpeakerEmbeddingExtractor(
     sherpa_onnx.SpeakerEmbeddingExtractorConfig(model=embed_path, num_threads=2, provider="cpu")
 )
 
-# 2. this repo's tiny gender head
+# 2. this repo's tiny gender head + its config (holds the label map)
 head_path = hf_hub_download("AfriSpeech/afrispeech-gender-id", "onnx/model.onnx")
-label_map = json.load(open(hf_hub_download("AfriSpeech/afrispeech-gender-id", "label_map.json")))
-hf_hub_download("AfriSpeech/afrispeech-gender-id", "config.json")  # not used, but see the repo's download-count note
+config = json.load(open(hf_hub_download("AfriSpeech/afrispeech-gender-id", "config.json")))
+label_map = config["label_map"]
 session = ort.InferenceSession(head_path, providers=["CPUExecutionProvider"])
 
 # 3. run on a 16 kHz mono wav file
@@ -2199,7 +2199,7 @@ whole-directory batch), built on the same `gender_id.py` helper.
 ## Files
 
 - `onnx/model.onnx` - the trained MLP head (embedding -> logits)
-- `label_map.json` - `{"0": "female", "1": "male"}` output index mapping
+- `config.json` - architecture metadata plus `label_map` (`{"0": "female", "1": "male"}`), the output-index mapping needed to interpret the head's output
 - `metrics.json` - full validation/test metrics, including the per-language table above
 - `scripts/gender_id.py` - reusable `GenderClassifier` class
 - `scripts/infer_file.py` - classify one audio file