test

README.md

@@ -1,16 +1,8 @@
 ---
-inference: true
+inference: false
 tags:
 - musicgen
 license: cc-by-nc-4.0
-pipeline_tag: text-to-audio
-widget:
-- text: "a funky house with 80s hip hop vibes"
-  example_title: "Prompt 1"
-- text: "a chill song with influences from lofi, chillstep and downtempo"
-  example_title: "Prompt 2"
-- text: "a catchy beat for a podcast intro"
-  example_title: "Prompt 3"  
 ---
 
 # MusicGen - Small - 300M
@@ -54,31 +46,18 @@ 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) and scipy:
+1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
 
 ```
-pip install --upgrade pip
-pip install --upgrade transformers scipy
+pip install git+https://github.com/huggingface/transformers.git
 ```
 
-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!
+2. Run the following Python code to generate text-conditional audio samples:
 
-```python
-from transformers import pipeline
-import scipy
-
-synthesiser = pipeline("text-to-audio", "facebook/musicgen-small")
-
-music = synthesiser("lo-fi music with a soothing melody", forward_params={"do_sample": True})
-
-scipy.io.wavfile.write("musicgen_out.wav", rate=music["sampling_rate"], data=music["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
+```py
 from transformers import AutoProcessor, MusicgenForConditionalGeneration
 
+
 processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
 model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
 
@@ -93,7 +72,7 @@ audio_values = model.generate(**inputs, max_new_tokens=256)
 
 3. Listen to the audio samples either in an ipynb notebook:
 
-```python
+```py
 from IPython.display import Audio
 
 sampling_rate = model.config.audio_encoder.sampling_rate
@@ -102,7 +81,7 @@ Audio(audio_values[0].numpy(), rate=sampling_rate)
 
 Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
 
-```python
+```py
 import scipy
 
 sampling_rate = model.config.audio_encoder.sampling_rate
@@ -122,7 +101,7 @@ pip install git+https://github.com/facebookresearch/audiocraft.git
 
 2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
 ```
-apt-get install ffmpeg
+apt get install ffmpeg
 ```
 
 3. Run the following Python code: