Duplicate from Plachta/ASTRAL-quantization

Co-authored-by: ElderFrog <Plachta@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,210 @@
+---
+license: gpl-3.0
+language:
+- en
+- zh
+- ja
+- kr
+- ru
+- ta
+- es
+- fr
+- de
+- it
+- pt
+- kn
+- nl
+pipeline_tag: automatic-speech-recognition
+---
+# Model Card for Model ID
+
+This 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.
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## 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
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### 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]

bsq2048/bsq2048_light.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7953115a60609c72a50bc79e88aa7248ffd4444b3912f89e8375ec1c6485fc6
+size 78181599

bsq2048/config.yml

@@ -0,0 +1,40 @@
+_target_: default_model.AstralQuantizer
+tokenizer_name: "openai/whisper-small"
+ssl_model_name: "facebook/hubert-large-ll60k"
+ssl_output_layer: 18
+encoder:
+  _target_: modules.convnext.ConvNeXtV2Stage
+  dim: 512
+  num_blocks: 12
+  intermediate_dim: 1536
+  dilation: 1
+  input_dim: 1024
+quantizer:
+  _target_: modules.bsq.BinarySphericalQuantize
+  codebook_size: 2048  # codebook size, must be a power of 2
+  dim: 512
+  entropy_loss_weight: 0.1
+  diversity_gamma: 1.0
+  spherical: True
+  enable_entropy_loss: True
+  soft_entropy_loss: True
+decoder:
+  _target_: modules.convnext.ConvNeXtV2Stage
+  dim: 512
+  num_blocks: 12
+  intermediate_dim: 1536
+  dilation: 1
+  output_dim: 1024
+  gin_channels: 192
+asr_decoder:
+  _target_: modules.asr_decoder.ASRDecoder
+  hidden_dim: 768
+  num_heads: 12
+  depth: 12
+  block_size: 4096
+  in_channels: 512
+  n_vocab: 51866
+  bos_id: 50528
+  eos_id: 50527
+  dropout_rate: 0.0
+  attn_dropout_rate: 0.0

bsq2048/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198cc8b2bbde6c1818cf44f748d146f80b08438532b6f0170ddbef78f7e98c2f
+size 1912057564

bsq32/bsq32_light.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01d6ba14a7af57ecc02b3eb5897a7e2abdaefab06b3f218d6709dc98b0e83a3
+size 78156693

bsq32/config.yml

@@ -0,0 +1,40 @@
+_target_: default_model.AstralQuantizer
+tokenizer_name: "openai/whisper-small"
+ssl_model_name: "facebook/hubert-large-ll60k"
+ssl_output_layer: 18
+encoder:
+  _target_: modules.convnext.ConvNeXtV2Stage
+  dim: 512
+  num_blocks: 12
+  intermediate_dim: 1536
+  dilation: 1
+  input_dim: 1024
+quantizer:
+  _target_: modules.bsq.BinarySphericalQuantize
+  codebook_size: 32  # codebook size, must be a power of 2
+  dim: 512
+  entropy_loss_weight: 0.1
+  diversity_gamma: 1.0
+  spherical: True
+  enable_entropy_loss: True
+  soft_entropy_loss: True
+decoder:
+  _target_: modules.convnext.ConvNeXtV2Stage
+  dim: 512
+  num_blocks: 12
+  intermediate_dim: 1536
+  dilation: 1
+  output_dim: 1024
+  gin_channels: 192
+asr_decoder:
+  _target_: modules.asr_decoder.ASRDecoder
+  hidden_dim: 768
+  num_heads: 12
+  depth: 12
+  block_size: 4096
+  in_channels: 512
+  n_vocab: 51866
+  bos_id: 50528
+  eos_id: 50527
+  dropout_rate: 0.0
+  attn_dropout_rate: 0.0

bsq32/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc023addd00827f1c462d096c9da37840c42421f64b36665a3207f6b8358ea5a
+size 1912031480