Atotti
/

llm-jp-4-8b-speech-chat

Audio-Text-to-Text

llama_for_speech_lm

Model card Files Files and versions

Atotti commited on Apr 5

Commit

a095c1b

·

verified ·

1 Parent(s): b5fe985

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -69,7 +69,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 tokenizer.pad_token = tokenizer.eos_token
 # Load audio
-waveform, sample_rate = torchaudio.load("sample.wav")
 if waveform.size(0) > 1:
     waveform = waveform.mean(dim=0, keepdim=True)
 waveform = waveform.squeeze(0)
@@ -192,7 +192,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 tokenizer.pad_token = tokenizer.eos_token
 # 音声読み込み
-waveform, sample_rate = torchaudio.load("sample.wav")
 if waveform.size(0) > 1:
     waveform = waveform.mean(dim=0, keepdim=True)
 waveform = waveform.squeeze(0)

 tokenizer.pad_token = tokenizer.eos_token
 # Load audio
+waveform, sample_rate = torchaudio.load("path/to/your_audio_file.wav")
 if waveform.size(0) > 1:
     waveform = waveform.mean(dim=0, keepdim=True)
 waveform = waveform.squeeze(0)
 tokenizer.pad_token = tokenizer.eos_token
 # 音声読み込み
+waveform, sample_rate = torchaudio.load("path/to/your_audio_file.wav")
 if waveform.size(0) > 1:
     waveform = waveform.mean(dim=0, keepdim=True)
 waveform = waveform.squeeze(0)