Update app.py

app.py

@@ -1,36 +1,20 @@
-import torch
-import gradio as gr
-from transformers import GPT2Tokenizer, GPT2LMHeadModel
+from transformers import AutoProcessor, SeamlessM4Tv2Model
+import torchaudio
+from IPython.display import Audio
 
-# Load pre-trained model and tokenizer
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
-model = GPT2LMHeadModel.from_pretrained("gpt2")
+processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large")
+model = SeamlessM4Tv2Model.from_pretrained("facebook/seamless-m4t-v2-large")
 
-# Define a function to generate text
-def generate_text(input_text):
-    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+# from text
+text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
+audio_array_from_text = model.generate(**text_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
 
-    # Generate text
-    with torch.no_grad():
-        output = model.generate(input_ids, max_length=100, no_repeat_ngram_size=True, do_sample=True, temperature=0.9)
-    
-    # Decode the generated text
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-    
-    return generated_text
+# from audio
+audio, orig_freq =  torchaudio.load("https://www2.cs.uic.edu/~i101/SoundFiles/preamble10.wav")
+audio =  torchaudio.functional.resample(audio, orig_freq=orig_freq, new_freq=16_000) # must be a 16 kHz waveform array
+audio_inputs = processor(audios=audio, return_tensors="pt")
+audio_array_from_audio = model.generate(**audio_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
 
-# Create a Gradio interface
-
-# Create a Gradio interface
-iface = gr.Interface(
-    generate_text,
-    gr.Textbox(lines=5, label="Input Text"),
-    "textbox",
-    examples=[
-        ["Once upon a time, in a land far, far away..."]
-    ],
-    title="GPT-2 Text Generation",
-    description="Enter some text and GPT-2 will generate more!",
-    theme="compact"
-)
-iface.launch()
+sample_rate = model.config.sampling_rate
+Audio(audio_array_from_text, rate=sample_rate)
+# Audio(audio_array_from_audio, rate=sample_rate)