Duplicate from NealCaren/TranscribeX

Co-authored-by: Neal Caren <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: TranscribeX
+emoji: 👀
+colorFrom: yellow
+colorTo: green
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: NealCaren/TranscribeX
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,71 @@
+import whisperx
+import streamlit as st
+import torch
+import tempfile
+import subprocess
+
+
+def transcribe(audio_file):
+
+
+    if torch.cuda.is_available():
+        device = "gpu"
+    else:
+        device = "cpu"
+    batch_size = 16 # reduce if low on GPU mem
+    compute_type = "int8" # change to "float16" if high on GPU mem (may reduce accuracy)
+    YOUR_HF_TOKEN = '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'
+
+    # load audio file
+    audio_bytes = uploaded_file.getvalue()
+    with open(temp_file, 'wb') as f:
+        f.write(audio_bytes)
+
+    # 1. Transcribe with original whisper (batched)
+    model = whisperx.load_model("tiny", device = device, compute_type=compute_type)
+
+    audio = whisperx.load_audio(temp_file)
+    result = model.transcribe(audio, batch_size=batch_size)
+    st.write("Transcribed! Here's what we have so far:")
+    st.write(result["segments"]) # before alignment
+
+    # delete model if low on GPU resources
+    # import gc; gc.collect(); torch.cuda.empty_cache(); del model
+
+    # 2. Align whisper output
+    model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device)
+    result = whisperx.align(result["segments"], model_a, metadata, audio, device, return_char_alignments=False)
+    st.write("Aligned! Here's what we have so far:")
+    st.write(result["segments"]) # after alignment
+
+    # delete model if low on GPU resources
+    # import gc; gc.collect(); torch.cuda.empty_cache(); del model_a
+
+    # 3. Assign speaker labels
+    diarize_model = whisperx.DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
+
+    # add min/max number of speakers if known
+    diarize_segments = diarize_model(audio_file)
+    # diarize_model(audio_file, min_speakers=min_speakers, max_speakers=max_speakers)
+
+    result = whisperx.assign_word_speakers(diarize_segments, result)
+    st.write(diarize_segments)
+    st.write(result["segments"]) # segments are now assigned speaker IDs
+
+
+st.title("Automated Transcription")
+
+form = st.form(key='my_form')
+uploaded_file = form.file_uploader("Choose a file")
+
+submit = form.form_submit_button("Transcribe!")
+
+
+if submit:
+    #temporary file to store audio_file
+    tmp_dir = tempfile.TemporaryDirectory()
+    temp_file = tmp_dir.name + '/mono.wav'
+    cmd = f"ffmpeg -y -i {uploaded_file} -acodec pcm_s16le -ar 16000 -ac 1 {temp_file}"
+    subprocess.Popen(cmd, shell=True).wait()
+
+    transcribe(temp_file)

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/m-bain/whisperx.git
+streamlit
+pandas