Upload README (1).md

README (1).md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: Jacaranda-Health/ASR-STT
+tags:
+- speech-to-text
+- automatic-speech-recognition
+- quantized
+- 8bit
+language:
+- en
+pipeline_tag: automatic-speech-recognition
+---
+
+# ASR-STT 8BIT Quantized
+
+This is a 8bit quantized version of [Jacaranda-Health/ASR-STT](https://huggingface.co/Jacaranda-Health/ASR-STT).
+
+## Model Details
+- **Base Model**: Jacaranda-Health/ASR-STT
+- **Quantization**: 8bit
+- **Size Reduction**: 73.1% smaller than original
+- **Original Size**: 2913.89 MB
+- **Quantized Size**: 784.94 MB
+
+## Usage
+
+```python
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, BitsAndBytesConfig
+import torch
+import librosa
+
+# Load processor
+processor = AutoProcessor.from_pretrained("eolang/ASR-STT-8bit")
+
+# Configure quantization
+quantization_config = BitsAndBytesConfig(
+    load_in_8bit=True
+    llm_int8_threshold=6.0,
+    llm_int8_has_fp16_weight=False
+    
+)
+
+# Load quantized model
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    "eolang/ASR-STT-8bit",
+    quantization_config=quantization_config,
+    device_map="auto"
+)
+
+# Transcription function
+def transcribe(filepath):
+    audio, sr = librosa.load(filepath, sr=16000)
+    inputs = processor(audio, sampling_rate=sr, return_tensors="pt")
+    
+    # Convert to half precision for quantized models
+    if torch.cuda.is_available():
+        inputs = {k: v.cuda().half() for k, v in inputs.items()}
+    else:
+        inputs = {k: v.half() for k, v in inputs.items()}
+    
+    with torch.no_grad():
+        generated_ids = model.generate(inputs["input_features"])
+    
+    return processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+# Example usage
+transcription = transcribe("path/to/audio.wav")
+print(transcription)
+```
+
+## Performance
+- Faster inference due to reduced precision
+- Lower memory usage
+- Maintained transcription quality
+
+## Requirements
+- transformers
+- torch
+- bitsandbytes
+- librosa