anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI/Build] Voxtral TTS Tests (#3738)

Browse Source 
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
This commit is contained in:
Clodagh Walsh authored and GitHub committed 2026-06-10 20:32:21 +08:00
1 parent 2fa4c7a4a9
commit aa92a3a35d
4 files changed
+159 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/offline_inference/text_to_speech/voxtral_tts/end2end.py
+1 -1
View File
@@ -212,7 +212,7 @@ def run_non_streaming(inputs, sampling_params_list, model_name, args, output_dir
output_audio_dur = 0.0
for batch_idx, o in enumerate(outputs):
audio_tensor = torch.cat(o.multimodal_output["audio"])
audio_tensor = torch.cat((o.multimodal_output["audio"],))
audio_array = audio_tensor.tolist()
output_audio_dur += float(len(audio_array)) / 24000
if args.write_audio: