Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 language:
 - ar
+- en
 license: apache-2.0
 tags:
 - text-to-speech
@@ -13,8 +14,6 @@ tags:
 - miratts
 - sofelia
 base_model: YatharthS/MiraTTS
-datasets:
-- hamdallah/ar-gemini
 library_name: transformers
 pipeline_tag: text-to-speech
 ---
@@ -22,7 +21,7 @@ pipeline_tag: text-to-speech
 <div style="text-align: center;">
   <h1>🇵🇸 Sofelia-TTS 🇵🇸</h1>
   <p><strong>Palestinian Arabic Text-to-Speech Model</strong></p>
-  <p><em>From the river to the sea, Palestine will be free</em> 🕊️</p>
+  <p><em>Palestine will be free</em> 🕊️</p>
 </div>
 
 ---
@@ -61,7 +60,7 @@ Built on top of [YatharthS/MiraTTS](https://huggingface.co/YatharthS/MiraTTS), S
 | **Base Model** | YatharthS/MiraTTS |
 | **Architecture** | Transformer-based Language Model + Audio Codec |
 | **Training Language** | Palestinian Arabic (ar-PS) |
-| **Dataset** | [hamdallah/ar-gemini](https://huggingface.co/datasets/hamdallah/ar-gemini) |
+| **Dataset** | Private Dataset |
 | **Sample Rate** | 16,000 Hz |
 | **License** | Apache 2.0 |
 | **Model Size** | ~1.3B parameters |
@@ -76,86 +75,23 @@ Built on top of [YatharthS/MiraTTS](https://huggingface.co/YatharthS/MiraTTS), S
 
 ```bash
 # Install required packages
-pip install torch transformers datasets
-pip install git+https://github.com/YatharthS/ncodec.git
+uv pip install git+https://github.com/ysharma3501/MiraTTS.git
 ```
 
 ### Usage (Python)
 
 ```python
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from ncodec.codec import TTSCodec
+from mira.model import MiraTTS
+from IPython.display import Audio
+mira_tts = MiraTTS('hamdallah/Sofelia-TTS') ## downloads model from huggingface
 
-# Load model and tokenizer
-model_id = "hamdallah/Sofelia-TTS"
-model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-
-# Initialize audio codec
-codec = TTSCodec()
-
-# Prepare your text (Palestinian Arabic)
+file = "reference_file.wav" ## can be mp3/wav/ogg or anything that librosa supports
 text = "مرحبا، كيف الحال؟ هذا نموذج للهجة الفلسطينية."
 
-# Load reference audio (3-10 seconds of speech)
-reference_audio_path = "path/to/reference_voice.wav"
-
-# Generate speech
-import torchaudio
-
-# Load and resample reference audio to 16kHz
-waveform, sample_rate = torchaudio.load(reference_audio_path)
-if sample_rate != 16000:
-    resampler = torchaudio.transforms.Resample(sample_rate, 16000)
-    waveform = resampler(waveform)
-
-# Encode reference audio to get context tokens
-audio_array = waveform.squeeze().numpy()
-semantic_tokens, context_tokens = codec.audio_encoder.encode(audio_array, True, duration=10)
-
-# Create prompt
-prompt = (
-    f"<|task_tts|><|start_text|>{text}<|end_text|>"
-    f"<|context_audio_start|>{context_tokens}<|context_audio_end|>"
-    f"<|prompt_speech_start|>{semantic_tokens}"
-)
-
-# Tokenize and generate
-inputs = tokenizer(prompt, return_tensors="pt")
-with torch.no_grad():
-    outputs = model.generate(
-        **inputs,
-        max_length=2048,
-        do_sample=True,
-        temperature=0.7,
-        top_p=0.95,
-    )
-
-# Decode to audio
-generated_text = tokenizer.decode(outputs[0], skip_special_tokens=False)
-audio_output = codec.decode(generated_text)
-
-# Save output
-torchaudio.save("output.wav", torch.from_numpy(audio_output).unsqueeze(0), 16000)
-print("✅ Audio saved to output.wav")
-```
+context_tokens = mira_tts.encode_audio(file)
+audio = mira_tts.generate(text, context_tokens)
 
-### Usage (CLI)
-
-If you have the training scripts:
-
-```bash
-# Clone the repository with inference scripts
-git clone https://huggingface.co/hamdallah/Sofelia-TTS
-cd Sofelia-TTS
-
-# Run inference
-python test_miratts.py \
-  --model-id hamdallah/Sofelia-TTS \
-  --audio-file reference_voice.wav \
-  --text "مرحباً من فلسطين الحرة" \
-  --output-file output.wav
+Audio(audio, rate=48000)
 ```
 
 ---
@@ -175,7 +111,7 @@ Try these Palestinian Arabic phrases:
 "الله يعطيك العافية"  # God give you wellness
 
 # About Palestine
-"فلسطين حرة من النهر إلى البحر"  # Palestine is free from the river to the sea
+"فلسطين حرة على طول"  # Palestine is free for ever
 "القدس عاصمة فلسطين الأبدية"     # Jerusalem is the eternal capital of Palestine
 "سنعود يوماً إلى ديارنا"         # We will return one day to our homes
 ```
@@ -186,7 +122,7 @@ Try these Palestinian Arabic phrases:
 
 ### Training Data
 
-- **Dataset**: [hamdallah/ar-gemini](https://huggingface.co/datasets/hamdallah/ar-gemini)
+- **Dataset**: 400 Hours Palestinian Speech
 - **Language**: Palestinian Arabic dialect
 - **Hours of audio**: High-quality Palestinian speech recordings
 - **Preprocessing**: Audio normalized and resampled to 16kHz
@@ -229,43 +165,33 @@ The model achieves:
 
 ## 🛠️ Advanced Usage
 
-### Adjusting Generation Parameters
+### Running the model using batching
 
 ```python
-# More creative/variable output
-outputs = model.generate(
-    **inputs,
-    max_length=2048,
-    do_sample=True,
-    temperature=0.9,  # Higher = more variation
-    top_p=0.95,
-    top_k=50,
-)
+file = "reference_file.wav" ## can be mp3/wav/ogg or anything that librosa supports
+text = ["مرحبا، كيف حالك؟", "بتعرف إنه انا بقدر احكي فلسطيني و English مع بعض Without Errors."]
 
-# More deterministic/stable output
-outputs = model.generate(
-    **inputs,
-    max_length=2048,
-    do_sample=True,
-    temperature=0.5,  # Lower = more stable
-    top_p=0.9,
-)
+context_tokens = [mira_tts.encode_audio(file)]
+
+audio = mira_tts.batch_generate(text, context_tokens)
+
+Audio(audio, rate=48000)
 ```
 
-### Batch Processing
+### Adjusting Generation Parameters
 
 ```python
-# Process multiple texts with the same reference voice
-texts = [
-    "مرحباً",
-    "كيف حالك؟",
-    "فلسطين حرة"
-]
-
-for i, text in enumerate(texts):
-    prompt = create_prompt(text, reference_audio)  # Your prompt creation function
-    outputs = model.generate(...)
-    save_audio(f"output_{i}.wav", outputs)
+# More creative/variable output
+
+mira_tts.set_params(
+    top_p=0.95, 
+    top_k=20, 
+    temperature=0.01, # Higher = more variation
+    max_new_tokens=1024, 
+    repetition_penalty=2.2, 
+    min_p=0.05
+)
+
 ```
 
 ---
@@ -306,7 +232,7 @@ This model captures these linguistic features, making it authentic and represent
 
 This model is dedicated to the Palestinian people and their enduring struggle for freedom, dignity, and justice. Through technology, we preserve and celebrate Palestinian culture, language, and identity.
 
-**Free Palestine** 🇵🇸 **From the River to the Sea**
+**Free Palestine** 🇵🇸
 
 > *"We will not be erased. Our voices will echo through time, in every language model, every algorithm, every line of code. Palestine lives, and so does its voice."*
 
@@ -335,14 +261,12 @@ This model is released under the **Apache 2.0 License**, making it free for:
 
 - **Model Repository**: [hamdallah/Sofelia-TTS](https://huggingface.co/hamdallah/Sofelia-TTS)
 - **Issues & Questions**: Use the Community tab or open an issue
-- **Dataset**: [hamdallah/ar-gemini](https://huggingface.co/datasets/hamdallah/ar-gemini)
 
 ---
 
 ## 🔗 Related Resources
 
 - [YatharthS/MiraTTS](https://huggingface.co/YatharthS/MiraTTS) - Base model
-- [hamdallah/ar-gemini](https://huggingface.co/datasets/hamdallah/ar-gemini) - Training dataset
 - [ncodec](https://github.com/YatharthS/ncodec) - Audio codec library
 
 ---
@@ -373,4 +297,4 @@ If you use this model in your research or projects, please cite:
 
 ---
 
-**Made with ❤️ for Palestine**
+**Made with ❤️ for Palestine**