Update README.md

README.md

@@ -1,206 +1,223 @@
 ---
+language:
+- ja
+license: apache-2.0
 base_model: openai/whisper-tiny
-library_name: peft
 tags:
-- base_model:adapter:openai/whisper-tiny
+- whisper
+- japanese
+- asr
+- speech-recognition
 - lora
-- transformers
+- peft
+- fine-tuned
+library_name: transformers
+metrics:
+- cer
+pipeline_tag: automatic-speech-recognition
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# whisper-tiny-ja-lora
 
+A LoRA-finetuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) for **Japanese Automatic Speech Recognition (ASR)**, trained on the [ReazonSpeech](https://huggingface.co/datasets/reazon-research/reazonspeech) dataset using Parameter-Efficient Fine-Tuning (PEFT/LoRA).
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-
+This model applies Low-Rank Adaptation (LoRA) on top of Whisper Tiny to improve Japanese transcription quality while keeping the number of trainable parameters small. LoRA adapters are merged post-training for easy deployment.
 
-- **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 type:** Automatic Speech Recognition (ASR)
+- **Language:** Japanese (ja)
+- **Base model:** [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
+- **Fine-tuning method:** LoRA (Low-Rank Adaptation) via PEFT
+- **License:** Apache 2.0
+- **Developed by:** [dungca](https://huggingface.co/dungca)
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Training repository:** [dungca1512/whisper-finetune-ja-train](https://github.com/dungca1512/whisper-finetune-ja-train)
+- **Base model:** [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
 
 ## 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]
+This model is designed for Japanese speech-to-text transcription tasks:
 
-### 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]
+- Transcribing Japanese audio files
+- Japanese voice assistants and conversational AI
+- Japanese language learning applications (e.g., pronunciation feedback)
+- Subtitle generation for Japanese audio/video content
 
 ### 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.
+- Non-Japanese speech (model is fine-tuned specifically for Japanese)
+- Real-time streaming ASR in latency-critical production systems (whisper-tiny architecture may not meet accuracy requirements)
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+### Load LoRA Adapter (PEFT)
+
+```python
+import torch
+from transformers import AutoProcessor, WhisperForConditionalGeneration
+from peft import PeftModel
+
+# Load base model and processor
+base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
+processor = AutoProcessor.from_pretrained("openai/whisper-tiny")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "dungca/whisper-tiny-ja-lora")
+model.eval()
+
+# Transcribe audio
+def transcribe(audio_array, sampling_rate=16000):
+    inputs = processor(
+        audio_array,
+        sampling_rate=sampling_rate,
+        return_tensors="pt"
+    )
+    with torch.no_grad():
+        predicted_ids = model.generate(
+            inputs["input_features"],
+            language="japanese",
+            task="transcribe"
+        )
+    return processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
+```
+
+### Quick Inference with Pipeline
+
+```python
+from transformers import pipeline
+from peft import PeftModel, PeftConfig
+from transformers import WhisperForConditionalGeneration, AutoProcessor
+
+config = PeftConfig.from_pretrained("dungca/whisper-tiny-ja-lora")
+base_model = WhisperForConditionalGeneration.from_pretrained(config.base_model_name_or_path)
+model = PeftModel.from_pretrained(base_model, "dungca/whisper-tiny-ja-lora")
+
+processor = AutoProcessor.from_pretrained(config.base_model_name_or_path)
+
+asr = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    generate_kwargs={"language": "japanese", "task": "transcribe"},
+)
+
+result = asr("your_audio.wav")
+print(result["text"])
+```
 
 ## 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]
+- **Dataset:** [ReazonSpeech](https://huggingface.co/datasets/reazon-research/reazonspeech) (`small` split)
+- **Language:** Japanese (ja)
+- ReazonSpeech is a large-scale Japanese speech corpus collected from broadcast TV, covering diverse speaking styles and topics.
 
 ### 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]
+#### LoRA Configuration
 
+| Parameter | Value |
+|---|---|
+| `lora_r` | 16 |
+| `lora_alpha` | 32 |
+| `lora_dropout` | 0.05 |
+| `target_modules` | `q_proj`, `v_proj` |
 
 #### 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. -->
+| Parameter | Value |
+|---|---|
+| Learning rate | `1e-5` |
+| Batch size | 32 |
+| Epochs | ~1.55 (3000 steps) |
+| Training regime | fp16 mixed precision |
+| Optimizer | AdamW |
 
-### Testing Data, Factors & Metrics
+#### Infrastructure
 
-#### Testing Data
+| | |
+|---|---|
+| **Hardware** | Kaggle GPU — NVIDIA P100 (16GB) |
+| **Cloud Provider** | Kaggle (Google Cloud) |
+| **Compute Region** | US |
+| **Framework** | Transformers + PEFT + Datasets |
+| **PEFT version** | 0.18.1 |
 
-<!-- This should link to a Dataset Card if possible. -->
+### MLOps Pipeline
 
-[More Information Needed]
+Training is fully automated via GitHub Actions:
+- **CI:** Syntax check + lightweight data validation on every push
+- **CT (Continuous Training):** Triggers Kaggle kernel for LoRA fine-tuning on data/code changes
+- **CD:** Quality gate checks CER before promoting model to HuggingFace Hub
 
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+## Evaluation
 
-[More Information Needed]
+### Testing Data
 
-#### Metrics
+Evaluated on the ReazonSpeech validation split.
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+### Metrics
 
-[More Information Needed]
+- **CER (Character Error Rate):** Lower is better. Standard metric for Japanese ASR (character-level, unlike WER used for English).
 
 ### 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
+| Metric | Value |
+|---|---|
+| **eval/cer** | **0.52497** (~52.5%) |
+| eval/loss | 1.17656 |
+| eval/runtime | 162.422s |
+| eval/samples_per_second | 12.314 |
+| eval/steps_per_second | 0.770 |
+| train/global_step | 3000 |
+| train/epoch | 1.547 |
+| train/grad_norm | 2.161 |
 
-[More Information Needed]
+> **Note:** CER of ~52.5% reflects the constraints of `whisper-tiny` (39M parameters) on a small training subset. A follow-up experiment with `whisper-small` and extended training is in progress and expected to significantly reduce CER.
 
-### 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]
+## Bias, Risks, and Limitations
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+- **Model size:** Whisper Tiny is optimized for speed and efficiency, not peak accuracy. Expect higher error rates on noisy audio, accented speech, or domain-specific vocabulary.
+- **Training data scope:** Trained on broadcast Japanese; may perform worse on conversational or dialectal Japanese.
+- **CER baseline:** The current CER reflects an early training checkpoint. Further training epochs and a larger model size (`whisper-small`) are expected to improve results.
 
-[More Information Needed]
+### Recommendations
 
-## More Information [optional]
+For production use cases requiring high accuracy, consider using [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) or waiting for the upcoming `whisper-small-ja-lora` checkpoint.
 
-[More Information Needed]
+## Citation
 
-## Model Card Authors [optional]
+If you use this model, please cite the base Whisper model and the LoRA/PEFT method:
 
-[More Information Needed]
+```bibtex
+@misc{radford2022whisper,
+  title={Robust Speech Recognition via Large-Scale Weak Supervision},
+  author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
+  year={2022},
+  eprint={2212.04356},
+  archivePrefix={arXiv}
+}
 
-## Model Card Contact
+@misc{hu2021lora,
+  title={LoRA: Low-Rank Adaptation of Large Language Models},
+  author={Hu, Edward J. and others},
+  year={2021},
+  eprint={2106.09685},
+  archivePrefix={arXiv}
+}
+```
 
-[More Information Needed]
-### Framework versions
+### Framework Versions
 
-- PEFT 0.18.1
+- PEFT: 0.18.1
+- Transformers: ≥4.36.0
+- PyTorch: ≥2.0.0