Update README.md

README.md

@@ -41,7 +41,7 @@ apt-get install git-lfs
 
 ```
 git lfs install
-git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml-fp16
+git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml-int8_float16
 ```
 
 ## Usage
@@ -49,10 +49,9 @@ git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml-fp16
 ```
 from faster_whisper import WhisperModel
 
-model_path = "vegam-whisper-medium-ml-fp16"
+model_path = "vegam-whisper-medium-ml-int8_float16"
 
-# Run on GPU with FP16
-model = WhisperModel(model_path, device="cuda", compute_type="float16")
+model = WhisperModel(model_path, device="cuda", compute_type="int8_float16")
 
 segments, info = model.transcribe("audio.mp3", beam_size=5)
 
@@ -67,9 +66,9 @@ for segment in segments:
 ```
 from faster_whisper import WhisperModel
 
-model_path = "vegam-whisper-medium-ml-fp16"
+model_path = "vegam-whisper-medium-ml-int8_float16"
 
-model = WhisperModel(model_path, device="cuda", compute_type="float16")
+model = WhisperModel(model_path, device="cuda", compute_type="int8_float16")
 
 
 segments, info = model.transcribe("00b38e80-80b8-4f70-babf-566e848879fc.webm", beam_size=5)
@@ -90,8 +89,8 @@ Note: The audio file [00b38e80-80b8-4f70-babf-566e848879fc.webm](https://hugging
 This conversion was possible with wonderful [CTranslate2 library](https://github.com/OpenNMT/CTranslate2) leveraging the [Transformers converter for OpenAI Whisper](https://opennmt.net/CTranslate2/guides/transformers.html#whisper).The original model was converted with the following command:
 
 ```
-ct2-transformers-converter --model thennal/whisper-medium-ml --output_dir vegam-whisper-medium-ml-fp16 \
---quantization float16
+ct2-transformers-converter --model thennal/whisper-medium-ml --output_dir vegam-whisper-medium-ml-int8_float16 \
+--quantization int8_float16
 ```
 
 ## Many Thanks to