Update README.md

## Training Details

### Training Data

The model was fine-tuned on the `Lagyamfi/akan_audio_processed` dataset from Hugging Face. This dataset contains Akan audio clips and corresponding transcriptions, including various augmented versions such as pitch-shifted and noise-added variants.

### Training Procedure

#### Preprocessing

- The audio was resampled to 16kHz.
- Text was tokenized into the appropriate input format for Whisper.

#### Training Hyperparameters

- **Training regime:** Mixed-precision (fp16) training
- **Batch size:** 4
- **Learning rate:** 1e-4
- **Gradient accumulation steps:** 2

#### Speeds, Sizes, Times

- **Total training time:** Approximately 30 minutes
- **Model checkpoint size:** Approximately 1.8GB

## Evaluation

### Testing Data, Factors & Metrics

#### Testing Data

The test data is sourced from the `Lagyamfi/akan_audio_processed` dataset on Hugging Face, which includes a separate test split specifically for evaluating the model’s performance.

#### Factors

Performance was evaluated across variations within the Akan language as represented in the dataset, including factors like audio clarity, accent, and background noise.

#### Metrics

The model’s performance is evaluated using the Word Error Rate (WER) metric, which measures the rate of errors in transcriptions by comparing the predicted transcription to the ground truth.

### Results

- **Word Error Rate (WER):** 0.3772

This WER indicates that approximately 37.72% of words in the transcriptions contain errors relative to the ground truth on the test dataset.

Files changed (1) hide show

README.md +38 -168

README.md CHANGED Viewed

@@ -1,199 +1,69 @@
 ---
 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
+tags:
+- whisper
+- ASR
+- Akan
+- low-resource-language
+- speech-recognition
+datasets:
+- Lagyamfi/akan_audio_processed
+language:
+- ak
+- tw
+metrics:
+- wer
+base_model:
+- openai/whisper-small
+pipeline_tag: automatic-speech-recognition
 ---
+# Model Card for Akan Whisper Model
 ## Model Details
 ### Model Description
+This model is a fine-tuned version of OpenAI's Whisper model, designed for Automatic Speech Recognition (ASR) on the Akan language, a low-resource language spoken in Ghana. The model was trained on a dataset containing Akan audio clips and corresponding transcriptions, enabling it to transcribe spoken Akan into text.
+- **Developed by:** Mark Atta Mensah
+- **Shared by:** Mark Atta Mensah
+- **Model type:** Automatic Speech Recognition (ASR)
+- **Language(s) (NLP):** Akan (Twi)
+- **Finetuned from model:** openai/whisper-small
 ## Uses
 ### Direct Use
+This model can be directly used for transcribing Akan speech into text. It is suitable for applications like voice assistants, transcription services, and other language-based solutions that require Akan language support.
+### Downstream Use
+This model can be fine-tuned further or incorporated into larger applications that require multi-language ASR capabilities or specific domain adaptation for Akan.
 ### Out-of-Scope Use
+The model is not suitable for languages other than Akan (Twi) and may not perform well on other low-resource languages without additional fine-tuning.
 ## Bias, Risks, and Limitations
+As with any ASR model, this model may have biases based on the dataset it was trained on. Potential biases in the training data could lead to underperformance on accents, dialects, or language variations not well represented in the data.
 ### Recommendations
+Users should be aware of these limitations and assess the model’s performance on specific applications before deployment.
 ## How to Get Started with the Model
+```python
+from transformers import WhisperForConditionalGeneration, WhisperProcessor
+model = WhisperForConditionalGeneration.from_pretrained("GiftMark/akan-whisper-model")
+processor = WhisperProcessor.from_pretrained("GiftMark/akan-whisper-model")
+def transcribe(audio_array):
+    inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt").input_features
+    predicted_ids = model.generate(inputs)
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
+    return transcription