Update model artifacts from automated training run

README.md

@@ -1,95 +1,206 @@
 ---
-language:
-- ja
+base_model: openai/whisper-tiny
+library_name: peft
 tags:
-- automatic-speech-recognition
-- speech
-- whisper
-- peft
+- base_model:adapter:openai/whisper-tiny
 - lora
-- japanese
-library_name: transformers
-base_model: openai/whisper-tiny
-pipeline_tag: automatic-speech-recognition
-datasets:
-- reazon-research/reazonspeech
-metrics:
-- cer
-- loss
-model-index:
-- name: whisper-tiny-ja-lora
-  results:
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: japanese-asr/ja_asr.reazonspeech_test
-      type: japanese-asr/ja_asr.reazonspeech_test
-      split: test
-    metrics:
-    - type: cer
-      name: Character Error Rate (CER)
-      value: 0.52497
-    - type: loss
-      name: Eval Loss
-      value: 1.17656
+- transformers
 ---
 
-# Whisper Tiny JA LoRA (ReazonSpeech)
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## 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
 
-LoRA adapter fine-tuned from `openai/whisper-tiny` for Japanese ASR.
+[More Information Needed]
 
-## Model Type
+## Citation [optional]
 
-This repository contains **LoRA adapter weights only**.  
-Use it on top of `openai/whisper-tiny`.
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
-- Base model: `openai/whisper-tiny`
-- Language: Japanese (`ja`)
-- Training method: LoRA (`q_proj`, `v_proj`)
-- Dataset: `reazon-research/reazonspeech` (gated)
+**BibTeX:**
 
-## Training Setup
+[More Information Needed]
 
-- Epochs (configured): `3`
-- Learning rate: `1e-5`
-- Batch size: `32`
-- LoRA r / alpha / dropout: `16 / 32 / 0.05`
-- Framework: `transformers`, `peft`
-- Runtime: Kaggle GPU P100
+**APA:**
 
-## Evaluation (Latest W&B Run)
+[More Information Needed]
 
-- `eval/cer`: **0.52497** (52.50%)
-- `eval/loss`: **1.17656**
-- `eval/runtime`: **162.422 s**
-- `eval/samples_per_second`: **12.314**
-- `eval/steps_per_second`: **0.77**
-- `train/global_step`: **3000**
-- `train/epoch`: **1.54719**
+## Glossary [optional]
 
-> Note: WER was not logged in this run.
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
 
-## Intended Use
+[More Information Needed]
 
-- Japanese speech-to-text transcription
-- Lightweight adapter training and deployment
+## More Information [optional]
 
-## Limitations
+[More Information Needed]
 
-- Quality depends on domain/audio condition match with training data
-- Not validated for safety-critical production use
-- Requires accepted access to gated dataset when reproducing training
+## Model Card Authors [optional]
 
-## Load Adapter
+[More Information Needed]
 
-```python
-from transformers import WhisperForConditionalGeneration, WhisperProcessor
-from peft import PeftModel
+## Model Card Contact
 
-base_model_id = "openai/whisper-tiny"
-adapter_id = "dungca/whisper-tiny-ja-lora"
+[More Information Needed]
+### Framework versions
 
-processor = WhisperProcessor.from_pretrained(base_model_id)
-base_model = WhisperForConditionalGeneration.from_pretrained(base_model_id)
-model = PeftModel.from_pretrained(base_model, adapter_id)
+- PEFT 0.18.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399be90d7e41e96d79ec6595ca699f80ea912ad509e8fd4b20b8ac6f1507622a
+oid sha256:c28b5a190f12421cffc4a96f8e28c478cf2cafac3552d550c526b6bc97619870
 size 1186320

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 1.5471892728210417,
-    "eval_cer": 0.5249730721665935,
-    "eval_loss": 1.176564335823059,
-    "eval_runtime": 162.422,
-    "eval_samples_per_second": 12.314,
-    "eval_steps_per_second": 0.77,
-    "total_flos": 2.4041315192832e+18,
-    "train_loss": 1.2634545720418295,
-    "train_runtime": 7050.8095,
-    "train_samples_per_second": 26.4,
-    "train_steps_per_second": 0.825
+    "epoch": 1.2893243940175347,
+    "eval_cer": 0.5345673594766027,
+    "eval_loss": 1.2403422594070435,
+    "eval_runtime": 156.1144,
+    "eval_samples_per_second": 12.811,
+    "eval_steps_per_second": 0.801,
+    "total_flos": 2.0034345848832e+18,
+    "train_loss": 1.294680369567871,
+    "train_runtime": 5838.1826,
+    "train_samples_per_second": 31.883,
+    "train_steps_per_second": 0.996
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.5471892728210417,
-    "eval_cer": 0.5249730721665935,
-    "eval_loss": 1.176564335823059,
-    "eval_runtime": 162.422,
-    "eval_samples_per_second": 12.314,
-    "eval_steps_per_second": 0.77
+    "epoch": 1.2893243940175347,
+    "eval_cer": 0.5345673594766027,
+    "eval_loss": 1.2403422594070435,
+    "eval_runtime": 156.1144,
+    "eval_samples_per_second": 12.811,
+    "eval_steps_per_second": 0.801
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.5471892728210417,
-    "total_flos": 2.4041315192832e+18,
-    "train_loss": 1.2634545720418295,
-    "train_runtime": 7050.8095,
-    "train_samples_per_second": 26.4,
-    "train_steps_per_second": 0.825
+    "epoch": 1.2893243940175347,
+    "total_flos": 2.0034345848832e+18,
+    "train_loss": 1.294680369567871,
+    "train_runtime": 5838.1826,
+    "train_samples_per_second": 31.883,
+    "train_steps_per_second": 0.996
 }