Update README.md

README.md

@@ -36,10 +36,10 @@ models: **6.3x faster than large-v3**, and 1.1x faster than distil-large-v2.
 | [distil-large-v2](https://huggingface.co/distil-whisper/distil-large-v2)     | 756        | 5.8          | 9.6        | 15.6                 | 11.6              |
 
 Since the sequential algorithm is the "de-facto" transcription algorithm across the most popular Whisper libraries 
-(Whisper cpp, Faster-Whisper, OpenAI Whisper), this distilled model is designed to be compatible across all libraries types. 
-Therefore, you can expect significant performance gains by switching from previous Distil-Whisper checkpoints to this latest one
-when using these Whisper libraries. For convenience, the weights for the most popular libraries are included in this repository, 
-with instructions for getting started [here](#library-integrations).
+(Whisper cpp, Faster-Whisper, OpenAI Whisper), this distilled model is designed to be compatible with these libraries. 
+You can expect significant performance gains by switching from previous Distil-Whisper checkpoints to distil-large-v3 
+when using these libraries. For convenience, the weights for the most popular libraries are already converted, 
+with instructions for getting started below.
 
 ## Table of Contents
 
@@ -60,7 +60,7 @@ with instructions for getting started [here](#library-integrations).
 
 ## Transformers Usage
 
-distil-large-v3 is supported in the Hugging Face 🤗 Transformers library from version 4.38 onwards. To run the model, first 
+distil-large-v3 is supported in the Hugging Face 🤗 Transformers library from version 4.39 onwards. To run the model, first 
 install the latest version of Transformers. For this example, we'll also install 🤗 Datasets to load a toy audio dataset 
 from the Hugging Face Hub:
 
@@ -261,10 +261,10 @@ inputs = inputs.to(device, dtype=torch_dtype)
 
 gen_kwargs = {
     "max_new_tokens": 448,
-    "num_beams": 1,  # set > 1 for beam-search
-    "condition_on_prev_tokens": False,  # condition for previous context
+    "num_beams": 1,
+    "condition_on_prev_tokens": False,
     "compression_ratio_threshold": 1.35,  # zlib compression ratio threshold (in token space)
-    "temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),  # temperature fallback
+    "temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
     "logprob_threshold": -1.0,
     "no_speech_threshold": 0.6,
     "return_timestamps": True,
@@ -446,7 +446,11 @@ Steps for getting started:
 git clone https://github.com/ggerganov/whisper.cpp.git
 cd whisper.cpp
 ```
-2. Download the GGML weights for distil-large-v3 from the Hugging Face Hub using the following Python snippet:
+2. Install the Hugging Face Hub Python package:
+```bash
+pip install --upgrade huggingface_hub
+```
+And download the GGML weights for distil-large-v3 using the following Python snippet:
 
 ```python
 from huggingface_hub import hf_hub_download
@@ -454,7 +458,7 @@ from huggingface_hub import hf_hub_download
 hf_hub_download(repo_id='distil-whisper/distil-large-v3-ggml', filename='ggml-distil-large-v3.bin', local_dir='./models')
 ```
 
-Note that if you do not have the `huggingface_hub` package installed, you can also download the weights with `wget`:
+Note that if you do not have a Python environment set-up, you can also download the weights directly with `wget`:
 
 ```bash
 wget https://huggingface.co/distil-whisper/distil-large-v3-ggml/resolve/main/ggml-distil-large-v3.bin -P ./models
@@ -524,17 +528,15 @@ The following code-snippet demonstrates how to transcribe a sample file from the
 🤗 Datasets:
 
 ```python
-import torch
-from datasets import load_dataset
 from huggingface_hub import hf_hub_download
+from datasets import load_dataset
 from whisper import load_model, transcribe
 
 model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3-openai", filename="model.bin")
 model = load_model(model_path)
 
 dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
-sample = dataset[0]["audio"]["array"]
-sample = torch.from_numpy(sample).float()
+sample = dataset[0]["audio"]["path"]
 
 pred_out = transcribe(model, audio=sample)
 print(pred_out["text"])