Update README.md

README.md

@@ -1,199 +1,118 @@
 ---
+license: cc-by-4.0
 library_name: transformers
-tags: []
+tags:
+- mimi
+- audio
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62611fcabbcbd1c34f1615f6/QPpyznxSH5CxjJ_mA0rdg.png)
 
+# Model Card for Mimi
 
+Mimi codec is a state-of-the-art audio neural codec, developped by [Kyutai](https://kyutai.org/), that combines semantic and acoustic information into audio tokens running at 12Hz and a bitrate of 1.1kbps.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+Mimi is a high-fidelity audio codec leveraging neural networks. It introduces a streaming encoder-decoder architecture with quantized latent space, trained in an end-to-end fashion. 
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+It was trained on speech data, which makes it particularly adapted to train speech language models or text-to-speech systems.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Developed by:**  Kyutai
+- **Model type:** Audio codec
+- **Audio types:** Speech
+- **License:** CC-BY
 
-### Model Sources [optional]
+### Model Sources 
 
-<!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [repo](https://github.com/kyutai-labs/moshi) 
+- **Paper:** [paper](http://kyutai.org/Moshi.pdf) 
+- **Demo:** [demo](https://moshi.chat/) 
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
+Use the following code to get started with the Mimi model using a dummy example from the LibriSpeech dataset (~9MB). First, install the required Python packages:
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+```
+pip install --upgrade pip
+pip install --upgrade datasets[audio]
+pip install git+https://github.com/huggingface/transformers.git@main
+```
 
-#### Speeds, Sizes, Times [optional]
+Then load an audio sample, and run a forward pass of the model:
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+```python
+from datasets import load_dataset, Audio
+from transformers import MimiModel, AutoFeatureExtractor
 
-[More Information Needed]
+# load a demonstration datasets
+librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
-## Evaluation
+# load the model + feature extractor (for pre-processing the audio)
+model = MimiModel.from_pretrained("kyutai/mimi")
+feature_extractor = AutoFeatureExtractor.from_pretrained("kyutai/mimi")
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+# cast the audio data to the correct sampling rate for the model
+librispeech_dummy = librispeech_dummy.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
+audio_sample = librispeech_dummy[0]["audio"]["array"]
 
-### Testing Data, Factors & Metrics
+# pre-process the inputs
+inputs = feature_extractor(raw_audio=audio_sample, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt")
 
-#### Testing Data
+# explicitly encode then decode the audio inputs
+encoder_outputs = model.encode(inputs["input_values"])
+audio_values = model.decode(encoder_outputs.audio_codes)[0]
 
-<!-- This should link to a Dataset Card if possible. -->
+# or the equivalent with a forward pass
+audio_values = model(inputs["input_values"]).audio_values
+```
 
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
+### Direct Use
 
-[More Information Needed]
+Mimi can be used directly as an audio codec for real-time compression and decompression of speech signals. 
+It provides high-quality audio compression and efficient decoding.
 
-## Citation [optional]
+### Out-of-Scope Use
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+The model is not intended to be used to impersonate other people or any malicious use of any kind. 
 
-**BibTeX:**
+## Bias, Risks, and Limitations
 
-[More Information Needed]
+The model has been trained with a few safeguards to try to limit potential toxic usages, however our toxicity analysis shows that it behaves in the middle of existing models with respect to textual generation. It has some bias towards certain domains and topics that are over-represented in the training data. Its capabilities are relatively limited so far and it is trained to produce only one voice to avoid impersonation. Yet, we need the perspective in time to establish the sociotechnical limitations. 
 
-**APA:**
+## How to Get Started with the Model
 
-[More Information Needed]
+See the main [README](https://github.com/kyutai-labs/moshi) file. 
 
-## Glossary [optional]
+## Training Details
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+### Training Data
 
-[More Information Needed]
+The training data is detailled in the paper. 
 
-## More Information [optional]
+### Training procedure and hyper-parameters
 
-[More Information Needed]
+The different stages of the training procedure are detailled in the paper along with the hyper-parameters. 
 
-## Model Card Authors [optional]
+## Citation 
 
-[More Information Needed]
+```
+@techreport{kyutai2024moshi,
+    author = {Alexandre D\'efossez and Laurent Mazar\'e and Manu Orsini and Am\'elie Royer and Patrick P\'erez and Herv\'e J\'egou and Edouard Grave and Neil Zeghidour},
+    title = {Moshi: a speech-text foundation model for real-time dialogue},
+    institution = {Kyutai},
+    year={2024},
+    month={September},
+    url={http://kyutai.org/Moshi.pdf},
+}
+```
 
-## Model Card Contact
+## Model Card Authors
 
-[More Information Needed]
+Alexandre Défossez, Laurent Mazaré, Manu Orsini, Amélie Royer, Patrick Pérez, Hervé Jégou, Edouard Grave, Neil Zeghidour, Yoach Lacombe