Update README.md

README.md

@@ -1,199 +1,170 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- text-to-speech
+- annotation
+license: apache-2.0
+language:
+- en
+- fr
+- es
+- pt
+- pl
+- de
+- nl
+- it
+pipeline_tag: text-to-speech
+inference: false
+datasets:
+- facebook/multilingual_librispeech
+- PHBJT/cml-tts-cleaned-levenshtein
+- PHBJT/multilingual_librispeech_text_description_capitalized
+- PPHBJT/cml-tts-description-punctuation-and-casing-restored
+- parler-tts/libritts_r_filtered
+- parler-tts/libritts-r-filtered-speaker-descriptions
+- parler-tts/mls_eng
+- parler-tts/mls-eng-speaker-descriptions
 ---
 
-# Model Card for Model ID
+<img src="https://huggingface.co/datasets/parler-tts/images/resolve/main/thumbnail.png" alt="Parler Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
 
-<!-- Provide a quick summary of what the model is/does. -->
 
+# Parler-TTS Mini v1.1 Multilingual
 
+<a target="_blank" href="https://huggingface.co/spaces/parler-tts/parler_tts">
+  <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
+</a>
 
-## Model Details
+**Parler-TTS Mini v1.1 Multilingual** is a multilingual extension of [Parler-TTS Mini](https://huggingface.co/parler-tts/parler-tts-mini-v1.1).
 
-### Model Description
+It is a fine-tuned version, trained on a [cleaned version](https://huggingface.co/datasets/PHBJT/cml-tts-cleaned-levenshtein) of [CML-TTS](https://huggingface.co/datasets/ylacombe/cml-tts) and on the non-English version of [Multilingual LibriSpeech](https://huggingface.co/datasets/facebook/multilingual_librispeech).
+In all, this represents some 9,200 hours of non-English data. To retain English capabilities, we also added back the [LibriTTS-R English dataset](https://huggingface.co/datasets/parler-tts/libritts_r_filtered), some 580h of high-quality English data.
 
-<!-- Provide a longer summary of what this model is. -->
+**Parler-TTS Mini v1.1 Multilingual** can speak in 7 European languages: English, French, Spanish, Portuguese, Polish, German, Italian and Dutch. 
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+Thanks to its **better prompt tokenizer**, it can easily be extended to other languages. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training.
 
-- **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]
+🚨 This work is the result of a collaboration between the **HuggingFace audio team** and the **[Quantum Squadra](https://quantumsquadra.com/) team**. The **[AI4Bharat](https://ai4bharat.iitm.ac.in/) team** also provided advice and assistance in improving tokenization. 🚨
 
-### Model Sources [optional]
 
-<!-- Provide the basic links for the model. -->
+## 📖 Quick Index
+* [👨‍💻 Installation](#👨‍💻-installation)
+* [🎲 Using a random voice](#🎲-random-voice)
+* [🎯 Using a specific speaker](#🎯-using-a-specific-speaker)
+* [Motivation](#motivation)
+* [Optimizing inference](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## 🛠️ Usage
 
-## Uses
+🚨Unlike previous versions of Parler-TTS, here we use two tokenizers - one for the prompt and one for the description.🚨
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### 👨‍💻 Installation
 
-### Direct Use
+Using Parler-TTS is as simple as "bonjour". Simply install the library once:
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```sh
+pip install git+https://github.com/huggingface/parler-tts.git
+```
 
-[More Information Needed]
+### 🎲 Random voice
 
-### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+**Parler-TTS** has been trained to generate speech with features that can be controlled with a simple text prompt, for example:
 
-[More Information Needed]
+```py
+import torch
+from parler_tts import ParlerTTSForConditionalGeneration
+from transformers import AutoTokenizer
+import soundfile as sf
 
-### Out-of-Scope Use
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-v1.1").to(device)
+tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1.1")
+description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)
 
-[More Information Needed]
+prompt = "Hey, how are you doing today?"
+description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
 
-## Bias, Risks, and Limitations
+input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)
+prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
+audio_arr = generation.cpu().numpy().squeeze()
+sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
+```
 
-[More Information Needed]
+### 🎯 Using a specific speaker
 
-### Recommendations
+To ensure speaker consistency across generations, this checkpoint was also trained on 34 speakers, characterized by name (e.g. Jon, Lea, Gary, Jenna, Mike, Laura).
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+To take advantage of this, simply adapt your text description to specify which speaker to use: `Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise.`
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+```py
+import torch
+from parler_tts import ParlerTTSForConditionalGeneration
+from transformers import AutoTokenizer
+import soundfile as sf
 
-## How to Get Started with the Model
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-Use the code below to get started with the model.
+model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-v1.1").to(device)
+tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1.1")
+description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)
 
-[More Information Needed]
+prompt = "Hey, how are you doing today?"
+description = "Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise."
 
-## Training Details
+input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)
+prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
 
-### Training Data
+generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
+audio_arr = generation.cpu().numpy().squeeze()
+sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
+```
 
-<!-- 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. -->
+**Tips**:
+* We've set up an [inference guide](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) to make generation faster. Think SDPA, torch.compile, batching and streaming!
+* Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise
+* Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech
+* The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt
 
-[More Information Needed]
+## Motivation
 
-### Training Procedure
+Parler-TTS is a reproduction of work from the paper [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://www.text-description-to-speech.com) by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively. 
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Contrarily to other TTS models, Parler-TTS is a **fully open-source** release. All of the datasets, pre-processing, training code and weights are released publicly under permissive license, enabling the community to build on our work and develop their own powerful TTS models.
+Parler-TTS was released alongside:
+* [The Parler-TTS repository](https://github.com/huggingface/parler-tts) - you can train and fine-tuned your own version of the model.
+* [The Data-Speech repository](https://github.com/huggingface/dataspeech) - a suite of utility scripts designed to annotate speech datasets.
+* [The Parler-TTS organization](https://huggingface.co/parler-tts) - where you can find the annotated datasets as well as the future checkpoints.
 
-#### Preprocessing [optional]
+## Citation
 
-[More Information Needed]
+If you found this repository useful, please consider citing this work and also the original Stability AI paper:
 
+```
+@misc{lacombe-etal-2024-parler-tts,
+  author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi},
+  title = {Parler-TTS},
+  year = {2024},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/huggingface/parler-tts}}
+}
+```
 
-#### Training Hyperparameters
+```
+@misc{lyth2024natural,
+      title={Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
+      author={Dan Lyth and Simon King},
+      year={2024},
+      eprint={2402.01912},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD}
+}
+```
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+## License
 
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[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
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+This model is permissively licensed under the Apache 2.0 license.