add Dockerfile

app.py

@@ -0,0 +1,35 @@
+from transformers import AutoProcessor, SeamlessM4Tv2Model
+import numpy as np
+#import torchaudio
+import sounddevice as sd
+#from audio
+
+processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large")
+model = SeamlessM4Tv2Model.from_pretrained("facebook/seamless-m4t-v2-large")
+
+# from text
+text_inputs = processor(text = "Искам da polucha zdravnata mi karta i помощ", src_lang="bul", return_tensors="pt")
+audio_array_from_text = model.generate(**text_inputs, tgt_lang="fra")[0].cpu().numpy().squeeze()
+
+# Afficher le tableau dans le terminal
+print(audio_array_from_text)
+
+# Optionnel : Afficher seulement les 10 premières valeurs pour éviter trop de sorties
+print(audio_array_from_text[:10])
+ 
+sd.play(audio_array_from_text, samplerate=16000)  # 16kHz est souvent utilisé par ces modèles
+sd.wait()
+
+
+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()
+
+# from audio
+output_tokens = model.generate(**audio_inputs, tgt_lang="fra", generate_speech=False)
+translated_text_from_audio = processor.decode(output_tokens[0].tolist()[0], skip_special_tokens=True)
+
+# from text
+output_tokens = model.generate(**text_inputs, tgt_lang="fra", generate_speech=False)
+translated_text_from_text = processor.decode(output_tokens[0].tolist()[0], skip_special_tokens=True)

requirements.txt

@@ -0,0 +1,8 @@
+Flask==2.0.3
+mlx
+mlx-lm
+
+transformers==4.11.3
+datasets==1.15.1
+huggingface-hub==0.1.0
+matplotlib==3.4.3