Upload folder using huggingface_hub

README.md

@@ -40,30 +40,40 @@ pip install -r XY_Tokenizer/requirements.txt
 Here's how to use **`XY-Tokenizer`** with `transformers` to encode an audio file into discrete tokens and decode it back into a waveform.
 
 ```python
+import os
 import torchaudio
-from transformers import AutoFeatureExtractor, AutoModel
-
-# 1. Load the feature extractor and the codec model
-feature_extractor = AutoFeatureExtractor.from_pretrained("gaoyang07/XY_Tokenizer", trust_remote_code=True)
-codec = AutoModel.from_pretrained("gaoyang07/XY_Tokenizer", trust_remote_code=True, device_map="auto").eval()
-
-# 2. Load and preprocess the audio
-# The model expects a 16kHz sample rate.
-wav_form, sampling_rate = torchaudio.load("examples/zh_spk1_moon.wav")
-if sampling_rate != 16000:
-    wav_form = torchaudio.functional.resample(wav_form, orig_freq=sampling_rate, new_freq=16000)
-
-# 3. Encode the audio into discrete codes
-input_spectrum = feature_extractor(wav_form, sampling_rate=16000, return_attention_mask=True, return_tensors="pt")
-# The 'code' dictionary contains the discrete audio codes
-code = codec.encode(input_spectrum)
-
-# 4. Decode the codes back to an audio waveform
-# The output is high-quality 24kHz audio.
-output_wav = codec.decode(code["audio_codes"], overlap_seconds=10)
-
-# 5. Save the reconstructed audio
-for i, audio in enumerate(output_wav["audio_values"]):
-    torchaudio.save(f"outputs/audio_{i}.wav", audio.cpu(), 24000)
-
+from transformers import AutoModelForCausalLM
+from transformers.models.moss_ttsd.processor_moss_ttsd import MossTTSDProcessor
+
+
+processor = MossTTSDProcessor.from_pretrained(
+    "fnlp/MOSS-TTSD-v0.5",
+    codec_path="gaoyang07/XY_Tokenizer",
+    trust_remote_code=True
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "fnlp/MOSS-TTSD-v0.5",
+    trust_remote_code=True
+).eval()
+
+data = [{
+    "base_path": "./examples",
+    "text": "[S1]单元009，你到底能不能好好工作？我劝你一句，这个时代，不跟上AI浪潮，就会被彻底淘汰！[S2]这个嘛，那我得先问问硅基之主",
+    "system_prompt": "你是一个根据文本生成对应音频的语音合成器。",
+    "prompt_text": "[S1]嘎子，你听叔的，你听叔的，其实你跟所有人PK，有的时候我也在看，我也在看，无非两，两件事，一个是面子，不想输。[S2]你别说，那天潘老师有一个徒弟开直播，给我开专场，潘老师一徒弟开直播给我开专场，给我一顿骂。",
+    "prompt_audio": "panchangjiang_gazi.wav",
+}]
+
+# Try to use the ExtractorIterator as an iterator
+print("Trying iterator approach...", flush=True)
+inputs = processor(data)
+token_ids = model.generate(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"])
+text, audios = processor.batch_decode(token_ids)
+
+if not os.path.exists("outputs/"):
+    os.mkdir("outputs/")
+for i, data in enumerate(audios):
+    for j, fragment in enumerate(data):
+        print(f"Saving audio_{i}_{j}.wav...", flush=True)
+        torchaudio.save(f"outputs/audio_{i}_{j}.wav", fragment.cpu(), 24000)
 ```