binant/ASTRAL-quantization

1---2license: gpl-3.03language:4- en5- zh6- ja7- kr8- ru9- ta10- es11- fr12- de13- it14- pt15- kn16- nl17pipeline_tag: automatic-speech-recognition18---19# Model Card for Model ID20 21This is a speech linguistic content quantizer operates on Hubert-large features. It is trained with explicit ASR supervision to preserve more linguistic content while discarding more speaker traits.22 23## Model Details24 25### Model Description26 27<!-- Provide a longer summary of what this model is. -->28 29 30 31- **Developed by:** [More Information Needed]32- **Funded by [optional]:** [More Information Needed]33- **Shared by [optional]:** [More Information Needed]34- **Model type:** [More Information Needed]35- **Language(s) (NLP):** [More Information Needed]36- **License:** [More Information Needed]37- **Finetuned from model [optional]:** [More Information Needed]38 39### Model Sources [optional]40 41<!-- Provide the basic links for the model. -->42 43- **Repository:** [More Information Needed]44- **Paper [optional]:** [More Information Needed]45- **Demo [optional]:** [More Information Needed]46 47## Uses48 49<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->50 51### Direct Use52 53<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->54 55[More Information Needed]56 57### Downstream Use [optional]58 59<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->60 61[More Information Needed]62 63### Out-of-Scope Use64 65<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->66 67[More Information Needed]68 69## Bias, Risks, and Limitations70 71<!-- This section is meant to convey both technical and sociotechnical limitations. -->72 73[More Information Needed]74 75### Recommendations76 77<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->78 79Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.80 81## How to Get Started with the Model82 83Use the code below to get started with the model.84 85[More Information Needed]86 87## Training Details88 89### Training Data90 91<!-- 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. -->92 93[More Information Needed]94 95### Training Procedure96 97<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->98 99#### Preprocessing [optional]100 101[More Information Needed]102 103 104#### Training Hyperparameters105 106- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->107 108#### Speeds, Sizes, Times [optional]109 110<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->111 112[More Information Needed]113 114## Evaluation115 116<!-- This section describes the evaluation protocols and provides the results. -->117 118### Testing Data, Factors & Metrics119 120#### Testing Data121 122<!-- This should link to a Dataset Card if possible. -->123 124[More Information Needed]125 126#### Factors127 128<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->129 130[More Information Needed]131 132#### Metrics133 134<!-- These are the evaluation metrics being used, ideally with a description of why. -->135 136[More Information Needed]137 138### Results139 140[More Information Needed]141 142#### Summary143 144 145 146## Model Examination [optional]147 148<!-- Relevant interpretability work for the model goes here -->149 150[More Information Needed]151 152## Environmental Impact153 154<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->155 156Carbon 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).157 158- **Hardware Type:** [More Information Needed]159- **Hours used:** [More Information Needed]160- **Cloud Provider:** [More Information Needed]161- **Compute Region:** [More Information Needed]162- **Carbon Emitted:** [More Information Needed]163 164## Technical Specifications [optional]165 166### Model Architecture and Objective167 168[More Information Needed]169 170### Compute Infrastructure171 172[More Information Needed]173 174#### Hardware175 176[More Information Needed]177 178#### Software179 180[More Information Needed]181 182## Citation [optional]183 184<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->185 186**BibTeX:**187 188[More Information Needed]189 190**APA:**191 192[More Information Needed]193 194## Glossary [optional]195 196<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->197 198[More Information Needed]199 200## More Information [optional]201 202[More Information Needed]203 204## Model Card Authors [optional]205 206[More Information Needed]207 208## Model Card Contact209 210[More Information Needed]