Update model card for Haitian Creole

README.md

@@ -1,48 +1,76 @@
----
-pipeline_tag: automatic-speech-recognition
-language: hat
-license: apache-2.0
-tags:
-  - trimmed
-  - whisper
-library_name: transformers
-base_model: openai/whisper-tiny
-base_model_relation: quantized
----
-
-# whisper-tiny-hat-32768
-
-This model is a vocabulary-pruned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
-optimised for **Haitian Creole** via the
-[trimming](https://huggingface.co/blog/introduction-to-trimming) method.
-
-Only the **decoder** token-embedding table and **lm_head** (proj_out) were pruned.
-The encoder is **fully unchanged**, so audio feature extraction is identical to
-the original model.
-
-## Vocabulary reduction
-
-| Component | Original | Pruned |
-|-----------|----------|--------|
-| vocab_size | 50258 | 31161 |
-| embed_tokens | 19.9M | 12.6M |
-| proj_out | 0.0M | 0.0M |
-| **Total** | **37.8M** | **30.4M** |
-
-## Usage
-
-```python
-from transformers import WhisperForConditionalGeneration, AutoTokenizer, pipeline
-
-model = WhisperForConditionalGeneration.from_pretrained("alphaedge-ai/whisper-tiny-hat-32768")
-tokenizer = AutoTokenizer.from_pretrained("alphaedge-ai/whisper-tiny-hat-32768")
-
-asr = pipeline("automatic-speech-recognition", model=model, tokenizer=tokenizer)
-result = asr("audio.wav", generate_kwargs={"language": "hat"})
-print(result["text"])
-```
-
-## ⚠️ Limitations
-
-Tokens not used in the selected language(s) were removed. The model may produce
-incorrect output for other languages.
+---
+pipeline_tag: automatic-speech-recognition
+language: hat
+license: apache-2.0
+tags:
+  - trimmed
+library_name: transformers
+base_model: openai/whisper-tiny
+base_model_relation: quantized
+datasets:
+  - lbourdois/fineweb-2-trimming
+---
+
+# whisper-tiny-hat-32768
+This model is a **19.42%% smaller** version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) optimized for **Haitian Creole** language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/lbourdois/introduction-to-trimming) method.  
+This trimmed model should perform similarly to the original model with only 32,768 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.
+
+## Model Statistics
+| Metric | Original | Trimmed | Reduction |
+|--------|----------|---------|-----------|
+| **Vocabulary size** | 51,865 tokens | 32,768 tokens | **36.82%** |
+| **Model size** | 37,760,640 params | 30,427,392 params | **19.42%** |
+
+![image](https://raw.githubusercontent.com/lbourdois/blog/refs/heads/master/assets/images/Trimming/whisper-tiny-32768.png)
+
+## Mining Dataset Statistics
+- **Number of texts used for mining**: 200,000 texts  
+- **Dataset**: [lbourdois/fineweb-2-trimming](https://huggingface.co/datasets/lbourdois/fineweb-2-trimming)
+
+## Usage
+```python
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+import librosa
+
+# Pipeline function
+processor = AutoProcessor.from_pretrained("alphaedge-ai/whisper-tiny-hat-32768")
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model="alphaedge-ai/whisper-tiny-hat-32768",
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    generate_kwargs={"language": "haitian creole", "task": "transcribe"},
+)
+
+# Loading and resampling at 16 kHz (required by Whisper)
+audio_array, sampling_rate = librosa.load(audio_path, sr=16000)
+
+# Result
+result = pipe(audio_array)
+print("Transcription :", result["text"])
+```
+
+## Citations
+
+#### Whisper
+```
+@misc{radford2022whisper,
+  doi = {10.48550/ARXIV.2212.04356},
+  url = {https://arxiv.org/abs/2212.04356},
+  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
+  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
+  publisher = {arXiv},
+  year = {2022},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```
+
+#### Trimming blog post
+```
+@misc{hf_blogpost_trimming,
+      title={Introduction to Trimming}, 
+      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
+      year={2026},
+      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
+}
+```