facebook
/

musicgen-stereo-large

@@ -11,6 +11,9 @@ We further release a set of stereophonic capable models. Those were fine tuned f
 from the mono models. The training data is otherwise identical and capabilities and limitations are shared with the base modes. The stereo models work by getting 2 streams of tokens from the EnCodec model, and interleaving those using
 the delay pattern.
 MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
 It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
 Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
@@ -67,15 +70,15 @@ pip install --upgrade git+https://github.com/huggingface/transformers.git scipy
 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!
 ```python
-import scipy
 import torch
 from transformers import pipeline
-synthesiser = pipeline("text-to-audio", "facebook/musicgen-stereo-large", torch_dtype=torch.float16, device="cuda")
-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"], 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.

 from the mono models. The training data is otherwise identical and capabilities and limitations are shared with the base modes. The stereo models work by getting 2 streams of tokens from the EnCodec model, and interleaving those using
 the delay pattern.
+Stereophonic sound, also known as stereo, is a technique used to reproduce sound with depth and direction.
+It uses two separate audio channels played through speakers (or headphones), which creates the impression of sound coming from multiple directions.
 MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
 It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
 Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
 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!
 ```python
 import torch
+import soundfile as sf
 from transformers import pipeline
+synthesiser = pipeline("text-to-audio", "facebook/musicgen-stereo-small", device="cuda:0", torch_dtype=torch.float16)
+music = synthesiser("lo-fi music with a soothing melody", forward_params={"max_new_tokens": 256})
+sf.write("musicgen_out.wav", music["audio"][0].T, music["sampling_rate"])
 ```
 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.