Update README.md

README.md

@@ -1,3 +1,84 @@
 ---
 license: mit
 ---
+
+# Teochew Whisper Medium
+
+This model is a fine-tuned version of the Whisper medium model to recognize the Teochew language (潮州话), a language in the Min Nan family spoken in southern China.
+
+For a detailed documentation of how this model was trained, please refer to this video: https://www.youtube.com/watch?v=JH_78KmP4Zk
+
+## Training Data
+
+The model was fine-tuned on approximately 35 hours of audio data derived from Teochew language movies, TV shows, and comedies.
+
+## Evaluation Metrics
+
+On our private test set, we obtained the following Word Error Rate (WER) metrics:
+
+- Careful Speech: 0.31
+- Conversational Speech: 0.68
+
+Known Limitations: this model has been trained on short audio clips and may struggle with audio that is longer than 10 seconds.
+
+## Example code
+
+The following script downloads the model and starts a demo using Gradio to run the model:
+
+```
+import torch
+import torchaudio
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+import gradio as gr
+
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+WHISPER_SAMPLE_RATE = 16000
+
+processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
+model = WhisperForConditionalGeneration.from_pretrained(
+    "efficient-nlp/teochew-whisper-medium"
+).to(DEVICE)
+
+
+def preprocess_audio(audio_path: str) -> torch.Tensor:
+    audio, sample_rate = torchaudio.load(audio_path)
+    # Resample if necessary
+    if sample_rate != WHISPER_SAMPLE_RATE:
+        resampler = torchaudio.transforms.Resample(
+            orig_freq=sample_rate, new_freq=WHISPER_SAMPLE_RATE
+        )
+        audio = resampler(audio)
+    # Convert to mono
+    if audio.shape[0] > 1:
+        audio = torch.mean(audio, dim=0)
+    return audio.squeeze()
+
+
+def transcribe(audio_path: str) -> str:
+    audio_input = preprocess_audio(audio_path)
+    input_features = processor(
+        audio_input,
+        sampling_rate=WHISPER_SAMPLE_RATE,
+        return_tensors="pt",
+        language="Chinese",
+    ).input_features.to(DEVICE)
+
+    forced_decoder_ids = processor.get_decoder_prompt_ids(
+        language="Chinese", task="transcribe"
+    )
+    predicted_ids = model.generate(
+        input_features, forced_decoder_ids=forced_decoder_ids
+    )
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
+    return transcription
+
+
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(type="filepath"),
+    outputs="text",
+    title="Teochew Speech Recognition",
+)
+iface.launch()
+```
+