Update README.md

README.md

@@ -1,9 +1,9 @@
 ---
-inference: false
+inference: true
 tags:
 - musicgen
 license: cc-by-nc-4.0
-pipeline_tag: text-to-audio
+pipeline_tag: text-to-speech
 ---
 
 # MusicGen - Small - 300M
@@ -47,17 +47,30 @@ Try out MusicGen yourself!
 
 You can run MusicGen locally with the 🤗 Transformers library from version 4.31.0 onwards.
 
-1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
+1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) and scipy:
 
 ```
-pip install git+https://github.com/huggingface/transformers.git
+pip install --upgrade pip
+pip install --upgrade transformers scipy
 ```
 
-2. Run the following Python code to generate text-conditional audio samples:
+2. Run inference via the `Text-to-Audio` (TTA) pipeline. You can infer the MusicGen model via the TTA pipeline in just a few lines of code!
 
-```py
-from transformers import AutoProcessor, MusicgenForConditionalGeneration
+```python
+from transformers import pipeline
+import scipy
 
+synthesiser = pipeline("text-to-audio", "facebook/musicgen-small")
+
+music = pipe("lo-fi music with a soothing melody", forward_params={"do_sample": True})
+
+scipy.io.wavfile.write("musicgen_out.wav", rate=music["sampling_rate"], music=audio["audio"])
+```
+
+3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 32 kHz audio waveform for more fine-grained control.
+
+```python
+from transformers import AutoProcessor, MusicgenForConditionalGeneration
 
 processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
 model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
@@ -73,7 +86,7 @@ audio_values = model.generate(**inputs, max_new_tokens=256)
 
 3. Listen to the audio samples either in an ipynb notebook:
 
-```py
+```python
 from IPython.display import Audio
 
 sampling_rate = model.config.audio_encoder.sampling_rate
@@ -82,7 +95,7 @@ Audio(audio_values[0].numpy(), rate=sampling_rate)
 
 Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
 
-```py
+```python
 import scipy
 
 sampling_rate = model.config.audio_encoder.sampling_rate