onnx-internal-testing/tiny-random-WhisperForConditionalGeneration-ONNX_external

1---2library_name: transformers3tags: []4---5 6# Model Card for Model ID7 8<!-- Provide a quick summary of what the model is/does. -->9 10## Code to create model11```py12import torch13from transformers import WhisperConfig, WhisperForConditionalGeneration, AutoProcessor14 15model_id = 'onnx-community/whisper-tiny.en'16config = WhisperConfig.from_pretrained(17    model_id,18    d_model=16,19    decoder_attention_heads=2,20    decoder_ffn_dim=64,21    decoder_layerdrop=0.0,22    decoder_layers=1,23    encoder_attention_heads=2,24    encoder_ffn_dim=64,25    encoder_layers=1,26    num_hidden_layers=1,27)28 29# Create model and randomize all weights30model = WhisperForConditionalGeneration(config)31 32torch.manual_seed(0) # Set for reproducibility33for name, param in model.named_parameters():34    param.data = torch.randn_like(param)35 36processor = AutoProcessor.from_pretrained(model_id)37```38 39## Model Details40 41### Model Description42 43<!-- Provide a longer summary of what this model is. -->44 45This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.46 47- **Developed by:** [More Information Needed]48- **Funded by [optional]:** [More Information Needed]49- **Shared by [optional]:** [More Information Needed]50- **Model type:** [More Information Needed]51- **Language(s) (NLP):** [More Information Needed]52- **License:** [More Information Needed]53- **Finetuned from model [optional]:** [More Information Needed]54 55### Model Sources [optional]56 57<!-- Provide the basic links for the model. -->58 59- **Repository:** [More Information Needed]60- **Paper [optional]:** [More Information Needed]61- **Demo [optional]:** [More Information Needed]62 63## Uses64 65<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->66 67### Direct Use68 69<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->70 71[More Information Needed]72 73### Downstream Use [optional]74 75<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->76 77[More Information Needed]78 79### Out-of-Scope Use80 81<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->82 83[More Information Needed]84 85## Bias, Risks, and Limitations86 87<!-- This section is meant to convey both technical and sociotechnical limitations. -->88 89[More Information Needed]90 91### Recommendations92 93<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->94 95Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.96 97## How to Get Started with the Model98 99Use the code below to get started with the model.100 101[More Information Needed]102 103## Training Details104 105### Training Data106 107<!-- 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. -->108 109[More Information Needed]110 111### Training Procedure112 113<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->114 115#### Preprocessing [optional]116 117[More Information Needed]118 119 120#### Training Hyperparameters121 122- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->123 124#### Speeds, Sizes, Times [optional]125 126<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->127 128[More Information Needed]129 130## Evaluation131 132<!-- This section describes the evaluation protocols and provides the results. -->133 134### Testing Data, Factors & Metrics135 136#### Testing Data137 138<!-- This should link to a Dataset Card if possible. -->139 140[More Information Needed]141 142#### Factors143 144<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->145 146[More Information Needed]147 148#### Metrics149 150<!-- These are the evaluation metrics being used, ideally with a description of why. -->151 152[More Information Needed]153 154### Results155 156[More Information Needed]157 158#### Summary159 160 161 162## Model Examination [optional]163 164<!-- Relevant interpretability work for the model goes here -->165 166[More Information Needed]167 168## Environmental Impact169 170<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->171 172Carbon 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).173 174- **Hardware Type:** [More Information Needed]175- **Hours used:** [More Information Needed]176- **Cloud Provider:** [More Information Needed]177- **Compute Region:** [More Information Needed]178- **Carbon Emitted:** [More Information Needed]179 180## Technical Specifications [optional]181 182### Model Architecture and Objective183 184[More Information Needed]185 186### Compute Infrastructure187 188[More Information Needed]189 190#### Hardware191 192[More Information Needed]193 194#### Software195 196[More Information Needed]197 198## Citation [optional]199 200<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->201 202**BibTeX:**203 204[More Information Needed]205 206**APA:**207 208[More Information Needed]209 210## Glossary [optional]211 212<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->213 214[More Information Needed]215 216## More Information [optional]217 218[More Information Needed]219 220## Model Card Authors [optional]221 222[More Information Needed]223 224## Model Card Contact225 226[More Information Needed]