Add Cohere Transcribe demo with uv + Python 3.14

.gitignore

@@ -0,0 +1,10 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

.python-version

@@ -0,0 +1 @@
+3.14

main.py

@@ -0,0 +1,6 @@
+def main():
+    print("Hello from cohere!")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -0,0 +1,15 @@
+[project]
+name = "cohere"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.14"
+dependencies = [
+    "huggingface-hub>=1.16.1",
+    "librosa>=0.11.0",
+    "protobuf>=7.35.0",
+    "sentencepiece>=0.2.1",
+    "soundfile>=0.13.1",
+    "torch>=2.12.0",
+    "transformers>=5.9.0",
+]

transcribe.py

@@ -0,0 +1,30 @@
+from transformers import AutoProcessor, CohereAsrForConditionalGeneration
+from transformers.audio_utils import load_audio
+from huggingface_hub import hf_hub_download
+
+# Load model
+print("Loading model...")
+processor = AutoProcessor.from_pretrained("CohereLabs/cohere-transcribe-03-2026")
+model = CohereAsrForConditionalGeneration.from_pretrained(
+    "CohereLabs/cohere-transcribe-03-2026",
+    device_map="auto"
+)
+
+# Download demo audio from Hugging Face
+audio_file = hf_hub_download(
+    repo_id="CohereLabs/cohere-transcribe-03-2026",
+    filename="demo/voxpopuli_test_en_demo.wav",
+)
+
+# Load audio
+audio = load_audio(audio_file, sampling_rate=16000)
+
+# Process and transcribe
+print("Transcribing...")
+inputs = processor(audio, sampling_rate=16000, return_tensors="pt", language="en")
+inputs.to(model.device, dtype=model.dtype)
+
+outputs = model.generate(**inputs, max_new_tokens=256)
+text = processor.decode(outputs, skip_special_tokens=True)
+
+print(f"\nTranscription:\n{text}\n")