Atotti
/

Google-USM

@@ -1,199 +1,76 @@
 ---
 library_name: transformers
-tags: []
 ---
-# 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. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **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]

 ---
 library_name: transformers
+license: gemma
 ---
+# google-usm: Extracted Gemma-3n Audio Encoder (USM)
+## モデル概要 (Model Description)
+このモデルは、Googleのマルチモーダルモデル [`google/gemma-3n-e2b-it`](https://huggingface.co/google/gemma-3n-e2b-it) から、**音声エンコーダー部分 (`audio_tower`) のみ**を抽出したものです。
+アーキテクチャは、論文 [Universal Speech Model](https://arxiv.org/abs/2303.01037) に基づく**Gemma3nAudioEncoder**です。
+このエンコーダーは、音声波形データを受け取り、その内容を表現する高次元の特徴量（エンコーディング）のシーケンスに変換する役割を果たします。
+## 主な用途 (Intended Use)
+このモデルは単体で音声認識（文字起こし）などを行うものではなく、より大きなモデルのコンポーネントとして使用されることを想定しています。
+* **マルチモーダルモデルの音声入力部として**: 生成AIに音声情報を与えるための特徴量を抽出します。
+* **音声分類**: このモデルの出力に分類ヘッドを追加して、特定の音声（例：笑い声、拍手、特定の単語）を分類するタスクでファインチューニングします。
+* **音声類似度検索**: 音声のエンコーディングをベクトルとして扱い、意味的に似た音声を検索します。
+* **話者認識**: 音声から話者を識別するタスクのベースモデルとして利用します。
+## 使用方法 (How to Use)
+このモデル（音声エンコーダー）と、元モデルの`Feature Extractor`を組み合わせて使用します。
+```python
+import torch
+import soundfile as sf
+from transformers import Gemma3nAudioEncoder, Gemma3nAudioFeatureExtractor
+encoder_id = "Atotti/google-usm"
+source_model_id = "google/gemma-3n-e2b-it"
+audio_encoder = Gemma3nAudioEncoder.from_pretrained(encoder_id)
+feature_extractor = Gemma3nAudioFeatureExtractor.from_pretrained(source_model_id)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+audio_encoder.to(device)
+audio_encoder.eval()
+waveform, sampling_rate = sf.read("/home/audio/J-SpAW-release/ASV/F001_R1_E1_M1_AA.wav")
+inputs = feature_extractor(
+    [waveform],
+    sampling_rate=sampling_rate,
+    return_tensors="pt"
+)
+audio_mel = inputs["input_features"].to(device)
+audio_mel_mask = (inputs["input_features_mask"] == 0).to(device)
+with torch.inference_mode():
+    audio_encodings, output_mask = audio_encoder(
+        audio_mel=audio_mel,
+        audio_mel_mask=audio_mel_mask
+    )
+print(audio_encodings.shape) # torch.Size([1, 18, 1536])
+print(audio_encodings[0, :5, :10])
+# tensor([[ 0.0014, -0.0044,  0.0003,  0.0084, -0.0076, -0.0194,  0.0071,  0.0160,
+#           0.0137,  0.0146],
+#         [-0.0153,  0.0051,  0.0111, -0.0134, -0.0032, -0.0134,  0.0112, -0.0163,
+#           0.0050,  0.0036],
+#         [ 0.0003, -0.0022,  0.0164, -0.0090, -0.0033, -0.0043,  0.0030, -0.0042,
+#          -0.0060,  0.0066],
+#         [-0.0006, -0.0194, -0.0006, -0.0097, -0.0049, -0.0132,  0.0012,  0.0175,
+#          -0.0242, -0.0091],
+#         [ 0.0127,  0.0122,  0.0125,  0.0277,  0.0116,  0.0152,  0.0142, -0.0099,
+#          -0.0080, -0.0233]], device='cuda:0')
+```